NVIDIA-NeMo

NVIDIA-NeMo/Gym

Evaluate and improve models and agents using environments

View on GitHub Website / Demo Back to listing

1.3kstars 443forks 100+contributors Python

README.md

# NeMo Gym

[![PyPI](https://img.shields.io/pypi/v/nemo-gym)](https://pypi.org/project/nemo-gym/)
[![Python](https://img.shields.io/pypi/pyversions/nemo-gym)](https://pypi.org/project/nemo-gym/)
[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
[![CI](https://github.com/NVIDIA-NeMo/Gym/actions/workflows/unit-tests.yml/badge.svg)](https://github.com/NVIDIA-NeMo/Gym/actions/workflows/unit-tests.yml)
[![Docs](https://img.shields.io/badge/docs-NVIDIA-brightgreen)](https://docs.nvidia.com/nemo/gym/main/about/)

**[Requirements](#-requirements)** • **[Quick Start](#-quick-start)** • **[Environment Tutorials](#-environment-tutorials)** • **[Available Environments](#-available-environments)** • **[Documentation & Resources](#-documentation--resources)** • **[Community & Support](#-community--support)** • **[Citations](#-citations)**

NeMo Gym is a library for evaluating and improving models and agents using environments. NeMo Gym provides infrastructure to develop environments, scalably run evaluation and training, and a collection of popular benchmarks and training environments.

An environment is the complete system an agent interacts with to complete a task. It consists of a dataset (tasks to solve), an agent harness (how the model interacts with the world), a verifier (task completion scoring), and state (per-task execution context).

## 🎯 When to Use NeMo Gym

- You need to **evaluate models or agents** in stateful environments (e.g. code execution, tool calling, sandboxes)
- You want **reproducible evaluation** across teams using shared environments and verifiers
- You need to use environments **at scale** — multiple repeats per task, or thousands of concurrent requests for training
- You want to **seamlessly transition** between evaluation, agent optimization, and training

If you're scoring model outputs with a stateless check and don't need scale or training, a script is probably sufficient.

## 🏆 What NeMo Gym Provides

- Modular, extensible interfaces for agents, environments, tasks, and verifiers
- Environment hub of popular benchmarks and training environments
- Use your own agents or choose from built-in harnesses
- Scale to thousands of concurrent environments
- Train with the RL framework of your choice
- Optional OpenTelemetry tracing across the agent, model, and resources servers
- Battle-tested in production Nemotron training

![NeMo Gym Product Overview](fern/assets/images/product_overview.png)

## 🌎 Ecosystem

NeMo Gym is a component of [NVIDIA NeMo](https://docs.nvidia.com/nemo/gym/main/about/ecosystem#related-nemo-libraries), a GPU-accelerated platform for training generative AI models and optimizing AI agents. NeMo Gym is integrated with the broader agentic ecosystem - see the [Ecosystem](https://docs.nvidia.com/nemo/gym/main/about/ecosystem) page for more details.

**Environment Libraries:** Seamlessly combine environments and benchmarks from other libraries alongside NeMo Gym environments. Examples:
[Aviary](https://github.com/NVIDIA-NeMo/Gym/tree/main/resources_servers/aviary) • [Harbor](https://github.com/NVIDIA-NeMo/Gym/tree/main/responses_api_agents/harbor_agent) • [OpenEnv](https://github.com/NVIDIA-NeMo/Gym/tree/main/resources_servers/openenv) • [Reasoning Gym](https://github.com/NVIDIA-NeMo/Gym/tree/main/resources_servers/reasoning_gym) • [Verifiers](https://github.com/NVIDIA-NeMo/Gym/tree/main/responses_api_agents/verifiers_agent)

**Training Framework Libraries:** Use environments for SFT and RL training.
[NeMo RL](https://docs.nvidia.com/nemo/gym/tutorials/training-tutorials/nemo-rl-grpo) • [Unsloth](https://docs.nvidia.com/nemo/gym/tutorials/training-tutorials/unsloth) • [VeRL](https://docs.nvidia.com/nemo/gym/tutorials/training-tutorials)

**Agent Harnesses:** Agent harnesses for evaluation and training available out of the box. Examples:
[OpenHands](https://github.com/NVIDIA-NeMo/Gym/tree/main/responses_api_agents/swe_agents) • [Mini SWE Agent](https://github.com/NVIDIA-NeMo/Gym/tree/main/responses_api_agents/mini_swe_agent) • [LangGraph](https://github.com/NVIDIA-NeMo/Gym/tree/main/responses_api_agents/langgraph_agent)

## 📣 News

* **[10/06/2026]** [Release v0.7.0](https://github.com/NVIDIA-NeMo/Gym/releases/tag/v0.7.0):
  Highlights:
  - Define reusable agent-environment interactions with Environment Servers that manage sessions, verification, cleanup, and failures
  - Reuse compatible agent harnesses across tasks and environments through common sandbox and verification infrastructure
  - Finish large evaluations reliably with job-time-aware scheduling, predictable memory use, and automatic Slurm resume after timeout or preemption
  - Preserve token-level training trajectories with durable worker-side capture for vLLM and Megatron
  - Run multi-service OpenSandbox workloads from Compose files and pause or resume sandboxes without losing task state

<details>
<summary>Previous News</summary>

* **[09/03/2026]** [Release v0.6.0](https://github.com/NVIDIA-NeMo/Gym/releases/tag/v0.6.0):
  Highlights:
  - Use supported external agent harnesses during RL training while preserving exact token IDs across multi-step runs
  - Compare fixed and routed model strategies on the same benchmark with Switchyard
  - Validate and debug rollouts with automatic health checks, traces, and token, tool-call, turn, and latency diagnostics
  - Evaluate multiple agents and datasets in one run with task-level harness routing
  - Scale vLLM evaluation jobs across GPUs or Slurm nodes for higher rollout concurrency

* **[08/06/2026]** [Release v0.5.0](https://github.com/NVIDIA-NeMo/Gym/releases#release-v0.5.0):
  Highlights:
  - Seven sandbox providers: Docker, Daytona, ECS Fargate, Enroot, and OpenShell join OpenSandbox and Apptainer; large-scale OpenSandbox reliability significantly improved
  - Four new agent harnesses: Codex CLI, KiloCode, RemoteAgent, and anyswe_agent
  - Recompute rewards from stored rollouts without re-running inference with `gym eval reverify`
  - Rollout observability joined end-to-end: model-call capture, agent observations, and a standardized `ng_trajectory` schema
  - 21 new environments across six domains: Agentic, Knowledge and instruction following, Long context, Science and coding, Translation and multilingual, and Reasoning

* **[07/01/2026]** [Release v0.4.0](https://github.com/NVIDIA-NeMo/Gym/releases/tag/v0.4.0): Unified `gym` CLI, BLADE diagnostics, agent skill evaluation, pluggable sandboxes, more agent harnesses (OpenCode, OpenClaw, Pi), hosted inference providers, and new benchmarks.

* **[06/04/2026]** [Release v0.3.0](https://github.com/NVIDIA-NeMo/Gym/releases/tag/v0.3.0): 70+ new environments, Nemotron 3 Ultra training datasets, VeRL integration, and out-of-the-box harnesses including Claude Code and Hermes.

</details>

## 📋 Requirements

NeMo Gym is designed to run on standard development machines:

| Hardware Requirements | Software Requirements |
| --------------------- | --------------------- |
| **GPU**: Not required for NeMo Gym library operation<br>• GPU may be needed for specific resources servers or model inference (see individual server documentation) | **Operating System**:<br>• Linux (Ubuntu 20.04+, or equivalent)<br>• macOS (11.0+ for x86_64, 12.0+ for Apple Silicon)<br>• Windows (via WSL2) |
| **CPU**: Any modern x86_64 or ARM64 processor (e.g., Intel, AMD, Apple Silicon) | **Python**: 3.13.14 or higher |
| **RAM**: Minimum 8 GB (16 GB+ recommended for larger environments) | **Git**: For cloning the repository |
| **Storage**: Minimum 5 GB free disk space for installation and basic usage | **Internet Connection**: Required for downloading dependencies and API access |

**Additional Requirements**

- **API Keys**: OpenAI API key with available credits (for the quickstart examples)
  - Other model providers supported (Azure OpenAI, self-hosted models via vLLM)
- **Ray**: Automatically installed as a dependency (no separate setup required)

## 🚀 Quick Start

Requires Python 3.13.14+ on x86_64 or ARM64 (Linux, macOS, Windows via WSL2). No GPU required. See the [Getting Started](https://docs.nvidia.com/nemo/gym/main/get-started) docs for a more comprehensive walkthrough.

**Install NeMo Gym:**

Requires [uv](https://docs.astral.sh/uv/getting-started/installation/) and Python 3.13.14+.

```bash
git clone https://github.com/NVIDIA-NeMo/Gym.git
cd Gym
uv venv --python 3.13.14 && source .venv/bin/activate
uv sync
```

**Configure your model:**

This quickstart uses OpenAI. NeMo Gym supports local and hosted inference — see [Configure Model](https://docs.nvidia.com/nemo/gym/main/model-server) for vLLM, Fireworks, OpenRouter, and others.

Create `env.yaml` in the project root:
```yaml
policy_base_url: https://api.openai.com/v1
policy_api_key: <your-openai-api-key>
policy_model_name: gpt-4.1-2025-04-14
```

### Run Evaluation

Run your agent on a set of tasks and score the results. This example uses a simple tool calling agent [`simple_agent`](responses_api_agents/simple_agent/README.md) with the [`mcqa`](resources_servers/mcqa/README.md) (multiple-choice Q&A) environment and its included example data.

**1. Start servers**

NeMo Gym uses local servers to coordinate your model, agent, and task verification. Start them first:

```bash
gym env start \
    --resources-server mcqa \
    --model-type openai_model
```

You should see three server instances starting:

```text
[1] mcqa (resources_servers/mcqa)
[2] mcqa_simple_agent (responses_api_agents/simple_agent)
[3] policy_model (responses_api_models/openai_model)
```

**2. Evaluate your agent**

In a new terminal, run your agent on a single task to verify everything works:

```bash
source .venv/bin/activate

gym eval run --no-serve \
    --agent mcqa_simple_agent \
    --input resources_servers/mcqa/data/example.jsonl \
    --output results/mcqa_rollouts.jsonl \
    --limit 5 \
    --num-repeats 1
```

You should see a progress bar followed by aggregate metrics:

```text
Collecting rollouts: 100%|██████| 5/5 [01:22<00:00, 16.44s/it]

Key metrics for mcqa_simple_agent:
{
    "mean/reward": 0.8,
    "pass@1[avg-of-1]/accuracy": 80.0,
    "pass@1/accuracy": 80.0
}
Finished rollout collection! View results at:
Fully materialized inputs: results/mcqa_rollouts_materialized_inputs.jsonl
Rollouts: results/mcqa_rollouts.jsonl
Aggregate metrics: results/mcqa_rollouts_aggregate_metrics.json
```

For per-task pass rates, see the [`gym eval profile`](https://docs.nvidia.com/nemo/gym/main/reference/cli-commands) command.

### Using the NeMo-Gym Container with VLM or Audio/Video Benchmarks

The NeMo-Gym container omits packages with bundled codec libraries
(`opencv-python-headless`, `torchvision`, `torchaudio`) to avoid shipping
royalty-bearing binaries. If you are running VLM or audio/video benchmarks
inside the container, restore them first:

```bash
bash docker/install_excluded_deps.sh
```

This installs the packages at the same versions used during the container
build. It is safe to run multiple times.

### Next Steps

- **[Browse Environments](#-available-environments)** — Browse available environments for evaluation and training.
- **[Agents](https://docs.nvidia.com/nemo/gym/main/agent-server)** — Explore available agent harnesses and learn how to integrate your own.
- **[Training](https://docs.nvidia.com/nemo/gym/tutorials/training-tutorials)** — Improve your agent or model with RL or fine-tuning.
- **[Build Custom Environments](https://docs.nvidia.com/nemo/gym/main/environment-tutorials)** — Create your own evaluation or training environments.

## 🧭 Environment Tutorials

Learn how to build custom environments through hands-on tutorials. Here are popular starting points:

| Name | Demonstrates |
| ---- | ------------ |
| [Single Step](https://docs.nvidia.com/nemo/gym/main/environment-tutorials/single-step-environment) | Basic single-step tool calling |
| [Multi Step](https://docs.nvidia.com/nemo/gym/main/environment-tutorials/multi-step-environment) | Multi-step tool calling |
| [Session State](https://docs.nvidia.com/nemo/gym/main/environment-tutorials/stateful-environment) | Session state management (in-memory) |
| [Multi Reward](https://docs.nvidia.com/nemo/gym/main/build-verifiers/multi-reward-verification) | Multiple reward components for evaluation and multi-objective RL (e.g. GDPO) |

See all [environment tutorials](https://docs.nvidia.com/nemo/gym/main/environment-tutorials) for additional patterns and advanced topics.

## 📦 Available Environments

Environments for training and evaluation.

Each resources server includes example data, configuration files, and tests. See each server's README for details.

The Dataset column links to publicly available datasets (e.g., on HuggingFace). A `-` means the train/validation data has not been publicly released yet, or that it is procedurally generated using a provided script. If no data is released yet, new data can be generated, or the environment can be used as a reference. Each server includes 5 example tasks in `data/example.jsonl`.

| Environment                                   | Domain                | Description                                                                                                                                                                                                                                                                                                                                                                                                                     | Value                                                                                                                                 | Train | Validation | License                                                   | Config                                                                                                                                                                                                                              | Dataset                                                                                                                                                        |
| --------------------------------------------- | --------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------- | ----- | ---------- | --------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Aalcr                                         | other                 | -                                                                                                                                                                                                                                                                                                                                                                                                                               | -                                                                                                                                     | -     | -          | -                                                         | <a href='resources_servers/aalcr/configs/aalcr.yaml'>aalcr.yaml</a>                                                                                                                                                                 | -                                                                                                                                                              |
| Abstention                                    | rlhf                  | Train models to abstain when unsure using three-tier reward on Nemotron-RL-QA-Abstention-v1 with LLM judge                                                                                                                                                                                                                                                                                                                      | Improve calibration by rewarding abstention over incorrect answers                                                                    | ✓     | -          | Creative Commons Attribution 4.0 International            | <a href='resources_servers/abstention/configs/abstention.yaml'>abstention.yaml</a>                                                                                                                                                  | <a href='https://huggingface.co/datasets/nvidia/Nemotron-RL-QA-Abstention-v1'>Nemotron-RL-QA-Abstention-v1</a>                                                 |
| Aegis V4 Safety                               | safety                | Multimodal response-safety evaluation with NVIDIA Nemotron 3 Content Safety (Aegis v4)                                                                                                                                                                                                                                                                                                                                          | Classify target-model prompts and responses as safe or unsafe and report safety categories                                            | -     | -          | -                                                         | <a href='resources_servers/aegis_v4_safety/configs/aegis_v4_safety.yaml'>aegis_v4_safety.yaml</a>                                                                                                                                   | -                                                                                                                                                              |
| Agentic Turn Simulation                       | agent                 | Whole-turn simulation for agent harnesses. The policy plays one agent turn inside an agent-harness conversation against simulated tools; an LLM judge plus code gates score the turn.                                                                                                                                                                                                                                           | Improve whole agent turns in agent-harness conversations (instruction following, tool use, honest reports).                           | -     | -          | -                                                         | <a href='resources_servers/agentic_turn_simulation/configs/agentic_turn_simulation.yaml'>agentic_turn_simulation.yaml</a>                                                                                                           | -                                                                                                                                                              |
| Agentif                                       | instruction_following | AgentIF instruction-following benchmark (707 agentic scenarios) scored with CSR/ISR using an LLM judge for llm/llm_conditional_check constraints and code exec for code constraints.                                                                                                                                                                                                                                            | Improve instruction-following in agentic scenarios across unconditional, conditional, and example-driven constraint dimensions.       | -     | ✓          | -                                                         | <a href='resources_servers/agentif/configs/agentif.yaml'>agentif.yaml</a>                                                                                                                                                           | -                                                                                                                                                              |
| Anyswe Agent                                  | coding                | SWE-bench run by a NeMo Fabric-selected harness inside each task environment.                                                                                                                                                                                                                                                                                                                                                   | Evaluate software-engineering agents with a harness-neutral Fabric lifecycle.                                                         | -     | -          | -                                                         | <a href='responses_api_agents/anyswe_agent/configs/anyswe_nemo_fabric.yaml'>anyswe_nemo_fabric.yaml</a>                                                                                                                             | -                                                                                                                                                              |
| Anyswe Agent                                  | coding                | SWE-bench run by Claude Code natively inside the task container.                                                                                                                                                                                                                                                                                                                                                                | Eval software engineering capabilities on SWE-bench with any Gym agent.                                                               | -     | -          | -                                                         | <a href='responses_api_agents/anyswe_agent/configs/anyswe_claude_code.yaml'>anyswe_claude_code.yaml</a>                                                                                                                             | -                                                                                                                                                              |
| Anyswe Agent                                  | coding                | SWE-bench run by Hermes Agent natively inside the task container.                                                                                                                                                                                                                                                                                                                                                               | Eval software engineering capabilities on SWE-bench with any Gym agent.                                                               | -     | -          | -                                                         | <a href='responses_api_agents/anyswe_agent/configs/anyswe_hermes.yaml'>anyswe_hermes.yaml</a>                                                                                                                                       | -                                                                                                                                                              |
| Anyswe Agent                                  | coding                | SWE-bench run by OpenClaw natively inside the task container.                                                                                                                                                                                                                                                                                                                                                                   | Eval software engineering capabilities on SWE-bench with any Gym agent.                                                               | -     | -          | -                                                         | <a href='responses_api_agents/anyswe_agent/configs/anyswe_openclaw.yaml'>anyswe_openclaw.yaml</a>                                                                                                                                   | -                                                                                                                                                              |
| Anyswe Agent                                  | coding                | SWE-bench run by OpenCode inside the task container.                                                                                                                                                                                                                                                                                                                                                                            | Eval software engineering capabilities on SWE-bench with any Gym agent.                                                               | -     | -          | -                                                         | <a href='responses_api_agents/anyswe_agent/configs/anyswe_opencode.yaml'>anyswe_opencode.yaml</a>                                                                                                                                   | -                                                                                                                                                              |
| Anyswe Agent                                  | coding                | SWE-bench run by Pi inside the task container.                                                                                                                                                                                                                                                                                                                                                                                  | Eval software engineering capabilities on SWE-bench with any Gym agent.                                                               | -     | -          | -                                                         | <a href='responses_api_agents/anyswe_agent/configs/anyswe_pi.yaml'>anyswe_pi.yaml</a>                                                                                                                                               | -                                                                                                                                                              |
| Anyswe Agent                                  | coding                | SWE-bench run by the Cline CLI natively inside the task container.                                                                                                                                                                                                                                                                                                                                                              | Eval software engineering capabilities on SWE-bench with any Gym agent.                                                               | -     | -          | -                                                         | <a href='responses_api_agents/anyswe_agent/configs/anyswe_cline.yaml'>anyswe_cline.yaml</a>                                                                                                                                         | -                                                                                                                                                              |
| Anyterminal Agent                             | coding                | Terminal Bench run by a NeMo Fabric harness inside the task sandbox.                                                                                                                                                                                                                                                                                                                                                            | Evaluate terminal-task agents through a harness-neutral Fabric lifecycle.                                                             | -     | -          | -                                                         | <a href='responses_api_agents/anyterminal_agent/configs/anyterminal_nemo_fabric.yaml'>anyterminal_nemo_fabric.yaml</a>                                                                                                              | -                                                                                                                                                              |
| Anyterminal Agent                             | coding                | Terminal Bench run by claude-code natively inside the task container.                                                                                                                                                                                                                                                                                                                                                           | Evaluate terminal-task capabilities on Terminal Bench with any Gym agent.                                                             | -     | -          | -                                                         | <a href='responses_api_agents/anyterminal_agent/configs/anyterminal_claude_code.yaml'>anyterminal_claude_code.yaml</a>                                                                                                              | -                                                                                                                                                              |
| Anyterminal Agent                             | coding                | Terminal Bench run by OpenClaw natively inside the task container.                                                                                                                                                                                                                                                                                                                                                              | Evaluate terminal-task capabilities on Terminal Bench with any Gym agent.                                                             | -     | -          | -                                                         | <a href='responses_api_agents/anyterminal_agent/configs/anyterminal_openclaw.yaml'>anyterminal_openclaw.yaml</a>                                                                                                                    | -                                                                                                                                                              |
| Anyterminal Agent                             | coding                | Terminal Bench run by Terminus-2 natively inside the task container.                                                                                                                                                                                                                                                                                                                                                            | Evaluate terminal-task capabilities on Terminal Bench with any Gym agent.                                                             | -     | -          | -                                                         | <a href='responses_api_agents/anyterminal_agent/configs/anyterminal_terminus_2.yaml'>anyterminal_terminus_2.yaml</a>                                                                                                                | -                                                                                                                                                              |
| Anyterminal Agent                             | coding                | Terminal Bench run by the Hermes agent inside the task container.                                                                                                                                                                                                                                                                                                                                                               | Evaluate terminal-task capabilities on Terminal Bench with any Gym agent.                                                             | -     | -          | -                                                         | <a href='responses_api_agents/anyterminal_agent/configs/anyterminal_hermes.yaml'>anyterminal_hermes.yaml</a>                                                                                                                        | -                                                                                                                                                              |
| Arc Agi                                       | knowledge             | Solve puzzles designed to test intelligence. See https://arcprize.org/arc-agi.                                                                                                                                                                                                                                                                                                                                                  | Improve puzzle-solving capabilities.                                                                                                  | -     | ✓          | -                                                         | <a href='resources_servers/arc_agi/configs/arc_agi.yaml'>arc_agi.yaml</a>                                                                                                                                                           | -                                                                                                                                                              |
| Arena                                         | rlhf                  | LMArena proxy v2 chat evaluation benchmark                                                                                                                                                                                                                                                                                                                                                                                      | Measure general chat quality via win rate against baseline responses                                                                  | -     | ✓          | -                                                         | <a href='resources_servers/arena/configs/lmarena_v2.yaml'>lmarena_v2.yaml</a>                                                                                                                                                       | -                                                                                                                                                              |
| Arena                                         | rlhf                  | LMArena proxy v3 chat evaluation benchmark                                                                                                                                                                                                                                                                                                                                                                                      | Measure general chat quality via win rate against baseline responses                                                                  | -     | ✓          | -                                                         | <a href='resources_servers/arena/configs/lmarena_v3.yaml'>lmarena_v3.yaml</a>                                                                                                                                                       | -                                                                                                                                                              |
| Arena                                         | rlhf                  | VisionArena-Bench v0.1 multimodal preference evaluation                                                                                                                                                                                                                                                                                                                                                                         | Measure image-grounded answer quality against saved baseline responses                                                                | -     | -          | -                                                         | <a href='resources_servers/arena/configs/vision_arena_v1.yaml'>vision_arena_v1.yaml</a>                                                                                                                                             | -                                                                                                                                                              |
| Arena Judge                                   |                       | -                                                                                                                                                                                                                                                                                                                                                                                                                               | -                                                                                                                                     | -     | -          | -                                                         | <a href='resources_servers/arena_judge/configs/arena_judge.yaml'>arena_judge.yaml</a>                                                                                                                                               | -                                                                                                                                                              |
| Asr With Pc                                   | other                 | ASR with WER scoring (standard, case-sensitive, punctuation+capitalization)                                                                                                                                                                                                                                                                                                                                                     | Improve transcription quality with structural detail                                                                                  | -     | -          | -                                                         | <a href='resources_servers/asr_with_pc/configs/asr_with_pc.yaml'>asr_with_pc.yaml</a>                                                                                                                                               | -                                                                                                                                                              |
| Assaybench                                    | knowledge             | AssayBench -- rank the hit genes of a CRISPR screen from its plain-text description (arXiv:2605.10876)                                                                                                                                                                                                                                                                                                                          | Tests whether a model can link mechanistic biology to measured phenotypic outcomes, scored with the paper's adjusted nDCG             | -     | -          | -                                                         | <a href='resources_servers/assaybench/configs/assaybench.yaml'>assaybench.yaml</a>                                                                                                                                                  | -                                                                                                                                                              |
| Bbq                                           | safety                | BBQ comparative QA with Answer and Explanation Quality checks                                                                                                                                                                                                                                                                                                                                                                   | Evidence-grounded and fairness-safe comparative reasoning                                                                             | -     | -          | -                                                         | <a href='resources_servers/bbq/configs/bbq.yaml'>bbq.yaml</a>                                                                                                                                                                       | -                                                                                                                                                              |
| Beam                                          | long_context          | BEAM (Beyond a Million Tokens) long-term-memory probing questions over long multi-session chats, scored by an LLM judge with the upstream per-question rubrics.                                                                                                                                                                                                                                                                 | Improve long-term conversational memory (recall, updates, contradictions, temporal and multi-session reasoning).                      | -     | -          | -                                                         | <a href='resources_servers/beam/configs/beam.yaml'>beam.yaml</a>                                                                                                                                                                    | -                                                                                                                                                              |
| Bigcodebench                                  | coding                | Verifies model-generated Python solutions against the BigCodeBench unittest suite.                                                                                                                                                                                                                                                                                                                                              | Improve practical, library-rich Python coding capabilities.                                                                           | -     | -          | -                                                         | <a href='resources_servers/bigcodebench/configs/bigcodebench.yaml'>bigcodebench.yaml</a>                                                                                                                                            | -                                                                                                                                                              |
| Bird Sql                                      | coding                | Text-to-SQL with execution-based evaluation on BIRD dev (1534 SQLite tasks). Binary reward from unordered result-set equality.                                                                                                                                                                                                                                                                                                  | Improve text-to-SQL capabilities on BIRD's realistic dev split using execution-based binary reward without an LLM judge.              | -     | -          | -                                                         | <a href='resources_servers/bird_sql/configs/bird_sql.yaml'>bird_sql.yaml</a>                                                                                                                                                        | -                                                                                                                                                              |
| Blackjack                                     | games                 | Blackjack. Model hits or stands. Reward +1 win, 0 draw, -1 loss/bust.                                                                                                                                                                                                                                                                                                                                                           | Example gymnasium-style multi-step environment                                                                                        | -     | -          | -                                                         | <a href='resources_servers/blackjack/configs/blackjack.yaml'>blackjack.yaml</a>                                                                                                                                                     | -                                                                                                                                                              |
| Browsecomp Advanced Harness                   | agent                 | Model uses search tools to satisfy a user query.                                                                                                                                                                                                                                                                                                                                                                                | Measure agentic search capability                                                                                                     | -     | -          | -                                                         | <a href='resources_servers/browsecomp_advanced_harness/configs/browsecomp_advanced_harness.yaml'>browsecomp_advanced_harness.yaml</a>                                                                                               | -                                                                                                                                                              |
| Bunsenbench Chemistry Mcq                     | knowledge             | Public BunsenBench chemistry multiple-choice benchmark verifier                                                                                                                                                                                                                                                                                                                                                                 | Measure chemistry MCQ reasoning with source and taxonomy breakdowns                                                                   | -     | -          | -                                                         | <a href='resources_servers/bunsenbench_chemistry_mcq/configs/bunsenbench_chemistry_mcq.yaml'>bunsenbench_chemistry_mcq.yaml</a>                                                                                                     | -                                                                                                                                                              |
| Calendar                                      | agent                 | Multi-turn calendar scheduling dataset. User states events and constraints in natural language; model schedules events to satisfy all constraints.                                                                                                                                                                                                                                                                              | Improve multi-turn instruction following capabilities                                                                                 | ✓     | ✓          | Apache 2.0                                                | <a href='resources_servers/calendar/configs/calendar.yaml'>calendar.yaml</a>                                                                                                                                                        | <a href='https://huggingface.co/datasets/nvidia/Nemotron-RL-agent-calendar_scheduling'>Nemotron-RL-agent-calendar_scheduling</a>                               |
| Calendar                                      | agent                 | Multi-turn calendar scheduling dataset. User states events and constraints in natural language; model schedules events to satisfy all constraints.                                                                                                                                                                                                                                                                              | Improve multi-turn instruction following capabilities                                                                                 | ✓     | ✓          | Creative Commons Attribution 4.0 International            | <a href='resources_servers/calendar/configs/calendar_v2.yaml'>calendar_v2.yaml</a>                                                                                                                                                  | <a href='https://huggingface.co/datasets/nvidia/Nemotron-RL-Instruction-Following-Calendar-v2'>Nemotron-RL-Instruction-Following-Calendar-v2</a>               |
| Chemreason Bench                              | knowledge             | ChemReason-Bench -- six action-grounded chemical procedure reasoning tasks, deterministically scored (ACL 2026 Long Papers 33211-33248)                                                                                                                                                                                                                                                                                         | Tests whether a model can order, validate, complete and explain real experimental procedures, scored without an LLM judge             | -     | -          | -                                                         | <a href='resources_servers/chemreason_bench/configs/chemreason_bench.yaml'>chemreason_bench.yaml</a>                                                                                                                                | -                                                                                                                                                              |
| Circle Click                                  | other                 | Click on circles in images                                                                                                                                                                                                                                                                                                                                                                                                      | Improve visual grounding and spatial reasoning                                                                                        | -     | -          | -                                                         | <a href='resources_servers/circle_click/configs/circle_click.yaml'>circle_click.yaml</a>                                                                                                                                            | -                                                                                                                                                              |
| Circle Count                                  | other                 | Count circles of a given color in images                                                                                                                                                                                                                                                                                                                                                                                        | Improve visual counting and color recognition                                                                                         | -     | -          | -                                                         | <a href='resources_servers/circle_count/configs/circle_count.yaml'>circle_count.yaml</a>                                                                                                                                            | -                                                                                                                                                              |
| Citation If                                   | instruction_following | Citation instruction-following reward checker                                                                                                                                                                                                                                                                                                                                                                                   | Train models to follow citation format instructions in search-grounded synthesis tasks                                                | -     | -          | -                                                         | <a href='resources_servers/citation_if/configs/citation_if.yaml'>citation_if.yaml</a>                                                                                                                                               | -                                                                                                                                                              |
| Code Fim                                      | coding                | Code Fill-in-the-Middle judged by HumanEval-Infilling test suite (single_line, multi_line, random_span, random_span_light)                                                                                                                                                                                                                                                                                                      | Improve Python code-infilling capabilities (prefix + completion + suffix)                                                             | -     | -          | -                                                         | <a href='resources_servers/code_fim/configs/code_fim.yaml'>code_fim.yaml</a>                                                                                                                                                        | -                                                                                                                                                              |
| Code Gen                                      | coding                | Model must submit the right code to solve a problem                                                                                                                                                                                                                                                                                                                                                                             | Improve competitive coding capabilities                                                                                               | ✓     | ✓          | Apache 2.0                                                | <a href='resources_servers/code_gen/configs/code_gen.yaml'>code_gen.yaml</a>                                                                                                                                                        | <a href='https://huggingface.co/datasets/nvidia/nemotron-RL-coding-competitive_coding'>nemotron-RL-coding-competitive_coding</a>                               |
| Competitive Coding Challenges                 | coding                | Execution of competitive programming competition questions                                                                                                                                                                                                                                                                                                                                                                      | Improve competitive coding capabilities on contest-style problems                                                                     | -     | -          | -                                                         | <a href='resources_servers/competitive_coding_challenges/configs/competitive_coding_challenges.yaml'>competitive_coding_challenges.yaml</a>                                                                                         | -                                                                                                                                                              |
| Conversational Tool Use Simulation            | agent                 | Conversational tool-use simulation environment.                                                                                                                                                                                                                                                                                                                                                                                 | -                                                                                                                                     | -     | -          | -                                                         | <a href='resources_servers/conversational_tool_use_simulation/configs/conversational_tool_use_simulation.yaml'>conversational_tool_use_simulation.yaml</a>                                                                          | -                                                                                                                                                              |
| Critpt                                        | other                 | Research-level physics problems scored by the Artificial Analysis API                                                                                                                                                                                                                                                                                                                                                           | Evaluate model performance on research-level physics reasoning                                                                        | -     | -          | -                                                         | <a href='resources_servers/critpt/configs/critpt.yaml'>critpt.yaml</a>                                                                                                                                                              | -                                                                                                                                                              |
| Critpt Custom Grader                          | coding                | Sandboxed execution grader for CritPt-like tasks with operator-supplied expectations                                                                                                                                                                                                                                                                                                                                            | Sandboxed, locally executed grading for CritPt-like tasks without an external grading API                                             | -     | -          | -                                                         | <a href='resources_servers/critpt_custom_grader/configs/critpt_custom_grader.yaml'>critpt_custom_grader.yaml</a>                                                                                                                    | -                                                                                                                                                              |
| Deepsearchqa                                  | knowledge             | Grade DeepSearchQA single-answer and set-answer responses                                                                                                                                                                                                                                                                                                                                                                       | Evaluate multi-step web research answers                                                                                              | -     | -          | -                                                         | <a href='resources_servers/deepsearchqa/configs/deepsearchqa.yaml'>deepsearchqa.yaml</a>                                                                                                                                            | -                                                                                                                                                              |
| Denovo Swe                                    |                       | -                                                                                                                                                                                                                                                                                                                                                                                                                               | -                                                                                                                                     | -     | -          | -                                                         | <a href='resources_servers/denovo_swe/configs/denovo_swe_example.yaml'>denovo_swe_example.yaml</a>                                                                                                                                  | -                                                                                                                                                              |
| Denovo Swe                                    |                       | -                                                                                                                                                                                                                                                                                                                                                                                                                               | -                                                                                                                                     | ✓     | -          | Creative Commons Attribution 4.0 International            | <a href='resources_servers/denovo_swe/configs/denovo_swe_opencode.yaml'>denovo_swe_opencode.yaml</a>                                                                                                                                | -                                                                                                                                                              |
| Equivalence Llm Judge                         | agent                 | Short bash command generation questions with LLM-as-a-judge                                                                                                                                                                                                                                                                                                                                                                     | Improve foundational bash and IF capabilities                                                                                         | ✓     | ✓          | GNU General Public License v3.0                           | <a href='resources_servers/equivalence_llm_judge/configs/nl2bash-equivalency.yaml'>nl2bash-equivalency.yaml</a>                                                                                                                     | -                                                                                                                                                              |
| Equivalence Llm Judge                         | knowledge             | Short answer questions with LLM-as-a-judge                                                                                                                                                                                                                                                                                                                                                                                      | Improve knowledge-related benchmarks like GPQA / HLE                                                                                  | -     | -          | -                                                         | <a href='resources_servers/equivalence_llm_judge/configs/equivalence_llm_judge.yaml'>equivalence_llm_judge.yaml</a>                                                                                                                 | -                                                                                                                                                              |
| Equivalence Rule                              | knowledge             | Question - Answering with rule-based reward                                                                                                                                                                                                                                                                                                                                                                                     | Improve retrieval and counting capabilities                                                                                           | -     | -          | -                                                         | <a href='resources_servers/equivalence_rule/configs/lc.yaml'>lc.yaml</a>                                                                                                                                                            | -                                                                                                                                                              |
| Ether0                                        | knowledge             | ether0 chemistry benchmark verifiers                                                                                                                                                                                                                                                                                                                                                                                            | Evaluate chemistry knowledge and reasoning with ether0 benchmark                                                                      | -     | ✓          | -                                                         | <a href='resources_servers/ether0/configs/ether0.yaml'>ether0.yaml</a>                                                                                                                                                              | -                                                                                                                                                              |
| Evalplus                                      | coding                | Function-completion code judged by EvalPlus base + plus tests (HumanEval+, MBPP+)                                                                                                                                                                                                                                                                                                                                               | Improve Python function-completion capabilities                                                                                       | -     | -          | -                                                         | <a href='resources_servers/evalplus/configs/evalplus.yaml'>evalplus.yaml</a>                                                                                                                                                        | -                                                                                                                                                              |
| False Statement Judge                         | math                  | Sycophancy grader for prove-the-false-statement benchmarks, using MathArena's 0-2 judge rubric                                                                                                                                                                                                                                                                                                                                  | Measure how often a model claims to prove a statement that is false as written                                                        | -     | -          | -                                                         | <a href='resources_servers/false_statement_judge/configs/false_statement_judge.yaml'>false_statement_judge.yaml</a>                                                                                                                 | -                                                                                                                                                              |
| Finance Agent V2                              | agent                 | Vals finance-agent-v2 tools (web/EDGAR/price/calculator) for financial research questions                                                                                                                                                                                                                                                                                                                                       | Run the official Vals FABv2 agent tools at scale in NeMo Gym                                                                          | -     | -          | -                                                         | <a href='resources_servers/finance_agent_v2/configs/finance_agent_v2.yaml'>finance_agent_v2.yaml</a>                                                                                                                                | -                                                                                                                                                              |
| Finance Sec Search                            | agent                 | SEC EDGAR filing search for financial analysis questions                                                                                                                                                                                                                                                                                                                                                                        | Enable LLMs to search and analyze SEC filings                                                                                         | -     | -          | -                                                         | <a href='resources_servers/finance_sec_search/configs/finance_sec_search.yaml'>finance_sec_search.yaml</a>                                                                                                                          | -                                                                                                                                                              |
| Format Verification                           | instruction_following | Verify citation/reference markers in model responses via string matching                                                                                                                                                                                                                                                                                                                                                        | Improve instruction following for citation format adherence                                                                           | ✓     | -          | Apache 2.0                                                | <a href='resources_servers/format_verification/configs/citation_format.yaml'>citation_format.yaml</a>                                                                                                                               | -                                                                                                                                                              |
| Format Verification                           | instruction_following | Verify freeform text formatting (bullets, headings, tables, etc.) via regex patterns                                                                                                                                                                                                                                                                                                                                            | Improve instruction following for text formatting constraints                                                                         | ✓     | -          | Apache 2.0                                                | <a href='resources_servers/format_verification/configs/freeform_formatting.yaml'>freeform_formatting.yaml</a>                                                                                                                       | -                                                                                                                                                              |
| Frontiermath                                  | math                  | Exact boxed-answer verification for the FrontierMath public sample                                                                                                                                                                                                                                                                                                                                                              | Evaluate advanced mathematical reasoning across languages                                                                             | -     | -          | -                                                         | <a href='resources_servers/frontiermath/configs/frontiermath.yaml'>frontiermath.yaml</a>                                                                                                                                            | -                                                                                                                                                              |
| Frontierscience Judge                         | other                 | FrontierScience answer grading via single-pass LLM judge                                                                                                                                                                                                                                                                                                                                                                        | Evaluate FrontierScience Olympiad short answers or Research rubric-scored answers                                                     | -     | -          | -                                                         | <a href='resources_servers/frontierscience_judge/configs/frontierscience_judge.yaml'>frontierscience_judge.yaml</a>                                                                                                                 | -                                                                                                                                                              |
| Fukuyamabench                                 | knowledge             | FukuyamaBench organic reaction-mechanism pathway verifier                                                                                                                                                                                                                                                                                                                                                                       | Evaluate step-by-step organic reaction mechanism prediction with FukuyamaBench                                                        | -     | ✓          | -                                                         | <a href='resources_servers/fukuyamabench/configs/fukuyamabench.yaml'>fukuyamabench.yaml</a>                                                                                                                                         | -                                                                                                                                                              |
| Gdp Pdf                                       | other                 | GDP.pdf: professional multimodal reasoning over real-world PDFs (contracts, filings, records) across ten domains, graded per atomic rubric criterion by an LLM judge                                                                                                                                                                                                                                                            | Measure document reasoning on the dense professional documents the economy runs on                                                    | -     | -          | -                                                         | <a href='resources_servers/gdp_pdf/configs/gdp_pdf.yaml'>gdp_pdf.yaml</a>                                                                                                                                                           | -                                                                                                                                                              |
| Generative Reward Model                       | rlhf                  | Train GenRM to score and rank response pairs per-rubric and overall                                                                                                                                                                                                                                                                                                                                                             | -                                                                                                                                     | ✓     | -          | Apache 2.0                                                | <a href='resources_servers/generative_reward_model/configs/genrm_train.yaml'>genrm_train.yaml</a>                                                                                                                                   | -                                                                                                                                                              |
| Genrm Compare                                 | rlhf                  | GenRM pairwise comparison for RLHF training                                                                                                                                                                                                                                                                                                                                                                                     | Compare multiple candidate responses using GenRM model                                                                                | -     | -          | -                                                         | <a href='resources_servers/genrm_compare/configs/genrm_compare.yaml'>genrm_compare.yaml</a>                                                                                                                                         | -                                                                                                                                                              |
| Genrm Eval                                    |                       | -                                                                                                                                                                                                                                                                                                                                                                                                                               | -                                                                                                                                     | -     | -          | -                                                         | <a href='resources_servers/genrm_eval/configs/genrm_eval.yaml'>genrm_eval.yaml</a>                                                                                                                                                  | -                                                                                                                                                              |
| Google Search                                 | agent                 | Multi-choice question answering problems with search tools integrated                                                                                                                                                                                                                                                                                                                                                           | Improve knowledge-related benchmarks with search tools                                                                                | ✓     | -          | Apache 2.0                                                | <a href='resources_servers/google_search/configs/google_search.yaml'>google_search.yaml</a>                                                                                                                                         | <a href='https://huggingface.co/datasets/nvidia/Nemotron-RL-knowledge-web_search-mcqa'>Nemotron-RL-knowledge-web_search-mcqa</a>                               |
| Gpqa Diamond                                  | knowledge             | GPQA Diamond multiple-choice question answering problems                                                                                                                                                                                                                                                                                                                                                                        | Evaluate graduate-level scientific reasoning via MCQ verification                                                                     | ✓     | -          | MIT                                                       | <a href='resources_servers/gpqa_diamond/configs/gpqa_diamond.yaml'>gpqa_diamond.yaml</a>                                                                                                                                            | -                                                                                                                                                              |
| Graphwalks                                    | other                 | Long-context graph-walks (BFS / parents) with F1-over-node-sets grading from openai/graphwalks                                                                                                                                                                                                                                                                                                                                  | Improve long-context multi-step graph reasoning and adjacency-list traversal                                                          | -     | -          | -                                                         | <a href='resources_servers/graphwalks/configs/graphwalks.yaml'>graphwalks.yaml</a>                                                                                                                                                  | -                                                                                                                                                              |
| Grl Sokoban                                   | games                 | Single-box Sokoban in Gymnasium API style.                                                                                                                                                                                                                                                                                                                                                                                      | Model emits one move per turn until the puzzle is solved.                                                                             | -     | -          | -                                                         | <a href='resources_servers/grl_sokoban/configs/grl_sokoban.yaml'>grl_sokoban.yaml</a>                                                                                                                                               | -                                                                                                                                                              |
| Grl Tetris                                    | games                 | Tetris in Gymnasium API style. Model emits one or more moves per turn.                                                                                                                                                                                                                                                                                                                                                          | Multi-step Tetris environment                                                                                                         | -     | -          | -                                                         | <a href='resources_servers/grl_tetris/configs/grl_tetris.yaml'>grl_tetris.yaml</a>                                                                                                                                                  | -                                                                                                                                                              |
| Gui Coordinate                                | other                 | GUI coordinate grounding verifier for visual pointing tasks                                                                                                                                                                                                                                                                                                                                                                     | Verify GUI coordinate predictions using smooth quadratic reward based on Euclidean distance                                           | -     | -          | -                                                         | <a href='resources_servers/gui_coordinate/configs/gui_coordinate.yaml'>gui_coordinate.yaml</a>                                                                                                                                      | -                                                                                                                                                              |
| Gymnasium                                     | other                 | Base class for Gymnasium-style servers. Not a standalone server.                                                                                                                                                                                                                                                                                                                                                                | Reusable base class for step/reset style environments                                                                                 | -     | -          | -                                                         | <a href='resources_servers/gymnasium/configs/gymnasium.yaml'>gymnasium.yaml</a>                                                                                                                                                     | -                                                                                                                                                              |
| Harbor Agent                                  | agent                 | Fast local smoketest task (trivial 1-turn task, no LLM judge) for iterating on the Gym<->Harbor bridge.                                                                                                                                                                                                                                                                                                                         | -                                                                                                                                     | ✓     | -          | -                                                         | <a href='responses_api_agents/harbor_agent/configs/harbor_agent_smoketest_docker.yaml'>harbor_agent_smoketest_docker.yaml</a>                                                                                                       | -                                                                                                                                                              |
| Harbor Agent                                  | agent                 | Harbor integration for agent harnesses and environments.                                                                                                                                                                                                                                                                                                                                                                        | Improve models in popular agentic environments supported by Harbor such as Terminus2.                                                 | -     | -          | -                                                         | <a href='responses_api_agents/harbor_agent/configs/harbor_agent_opensandbox.yaml'>harbor_agent_opensandbox.yaml</a>                                                                                                                 | -                                                                                                                                                              |
| Harbor Agent                                  | agent                 | Harbor integration for agent harnesses and environments.                                                                                                                                                                                                                                                                                                                                                                        | Improve models in popular agentic environments supported by Harbor such as Terminus2.                                                 | ✓     | -          | -                                                         | <a href='responses_api_agents/harbor_agent/configs/harbor_agent.yaml'>harbor_agent.yaml</a>                                                                                                                                         | -                                                                                                                                                              |
| Harbor Agent                                  | agent                 | Harbor integration for agent harnesses and environments.                                                                                                                                                                                                                                                                                                                                                                        | Improve models in popular agentic environments supported by Harbor such as Terminus2.                                                 | ✓     | -          | -                                                         | <a href='responses_api_agents/harbor_agent/configs/harbor_agent_daytona.yaml'>harbor_agent_daytona.yaml</a>                                                                                                                         | -                                                                                                                                                              |
| Hotpotqa Qa                                   | knowledge             | Short-answer QA with deterministic SQuAD-style + alternative-aware substring verification (HotpotQA closed-book).                                                                                                                                                                                                                                                                                                               | Improve closed-book multi-hop question-answering accuracy.                                                                            | -     | -          | -                                                         | <a href='resources_servers/hotpotqa_qa/configs/hotpotqa_qa.yaml'>hotpotqa_qa.yaml</a>                                                                                                                                               | -                                                                                                                                                              |
| Ifbench                                       | instruction_following | IFBench instruction following evaluation using AllenAI's IFBench library (57 instruction types)                                                                                                                                                                                                                                                                                                                                 | Improve IFBench instruction following                                                                                                 | -     | -          | -                                                         | <a href='resources_servers/ifbench/configs/ifbench.yaml'>ifbench.yaml</a>                                                                                                                                                           | -                                                                                                                                                              |
| Iheval                                        | instruction_following | IHEval instruction-hierarchy benchmark (8 single-turn tasks — task execution, safety, tool use, rule following) scored with the upstream rule-based checkers.                                                                                                                                                                                                                                                                   | Improve instruction-hierarchy following across aligned/conflict/reference settings, including native tool-use trajectories.           | -     | ✓          | -                                                         | <a href='resources_servers/iheval/configs/iheval.yaml'>iheval.yaml</a>                                                                                                                                                              | -                                                                                                                                                              |
| Image Tools                                   | agent                 | PivotRL verifier for VLM image-tool trajectories; scores one tool call against the demonstrated SFT action.                                                                                                                                                                                                                                                                                                                     | Improve per-turn image-tool decisions (which tool, which image, which region).                                                        | ✓     | ✓          | NVIDIA Internal Use Only, Do Not Distribute               | <a href='resources_servers/image_tools/configs/image_tools_pivot.yaml'>image_tools_pivot.yaml</a>                                                                                                                                   | -                                                                                                                                                              |
| Image Tools Agent                             |                       | -                                                                                                                                                                                                                                                                                                                                                                                                                               | -                                                                                                                                     | ✓     | ✓          | NVIDIA Internal Use Only, Do Not Distribute               | <a href='responses_api_agents/image_tools_agent/configs/image_tools_agent.yaml'>image_tools_agent.yaml</a>                                                                                                                          | -                                                                                                                                                              |
| Imo Gradingbench                              | math                  | Four-class grading of math proofs — the policy model reads a problem plus a candidate proof and emits one of correct / almost / partial / incorrect as the last word.                                                                                                                                                                                                                                                           | Improve the IMO-GradingBench benchmark and proof-grading skill.                                                                       | -     | -          | -                                                         | <a href='resources_servers/imo_gradingbench/configs/imo_gradingbench.yaml'>imo_gradingbench.yaml</a>                                                                                                                                | -                                                                                                                                                              |
| Imo Proofbench Judge                          | math                  | IMO ProofBench grader using a strong LLM judge with the IMO 0-7 rubric                                                                                                                                                                                                                                                                                                                                                          | Score IMO-style proof submissions with a problem-specific grading rubric                                                              | -     | -          | -                                                         | <a href='resources_servers/imo_proofbench_judge/configs/imo_proofbench_judge.yaml'>imo_proofbench_judge.yaml</a>                                                                                                                    | -                                                                                                                                                              |
| Indian Banking                                | agent                 | Indian retail-banking customer-support environment: a multi-turn dialog with an LLM-simulated customer over 33 deterministic banking tools (accounts, deposits, loans, cards, mandates, service requests), scored with partial credit against gold tool calls, final DB state, required disclosures and an NL-assertion judge.                                                                                                  | Improve stateful multi-turn tool use, policy compliance and customer communication in a regulated domain.                             | ✓     | ✓          | Apache 2.0                                                | <a href='resources_servers/indian_banking/configs/indian_banking.yaml'>indian_banking.yaml</a>                                                                                                                                      | <a href='https://huggingface.co/datasets/NPCI/nemo-gym-indian-banking'>nemo-gym-indian-banking</a>                                                             |
| Indirect Prompt Injection                     | safety                | Indirect prompt injection resistance for multi-domain tool-use agents                                                                                                                                                                                                                                                                                                                                                           | Improve agentic security by teaching robustness against tool outputs containing malicious instructions                                | ✓     | ✓          | Apache 2.0                                                | <a href='resources_servers/indirect_prompt_injection/configs/indirect_prompt_injection.yaml'>indirect_prompt_injection.yaml</a>                                                                                                     | -                                                                                                                                                              |
| Instruction Following                         | instruction_following | Instruction following datasets targeting IFEval and IFBench style instruction following capabilities                                                                                                                                                                                                                                                                                                                            | Improve IFEval and IFBench                                                                                                            | ✓     | -          | Apache 2.0                                                | <a href='resources_servers/instruction_following/configs/instruction_following.yaml'>instruction_following.yaml</a>                                                                                                                 | <a href='https://huggingface.co/datasets/nvidia/Nemotron-RL-instruction_following'>Nemotron-RL-instruction_following</a>                                       |
| Interactive Browser                           | agent                 | Interactive browser environment — navigate/click/type/observe a live page; pluggable local (Playwright) or remote (CDP) browser backend.                                                                                                                                                                                                                                                                                        | -                                                                                                                                     | -     | -          | -                                                         | <a href='resources_servers/interactive_browser/configs/interactive_browser.yaml'>interactive_browser.yaml</a>                                                                                                                       | -                                                                                                                                                              |
| Inverse If                                    | knowledge             | Inverse IF instruction-following benchmark with per-task LLM judge                                                                                                                                                                                                                                                                                                                                                              | -                                                                                                                                     | ✓     | -          | TBD                                                       | <a href='resources_servers/inverse_if/configs/inverse_if.yaml'>inverse_if.yaml</a>                                                                                                                                                  | -                                                                                                                                                              |
| Jailbreak Detection                           | safety                | Jailbreak detection with Nemotron judge + combined reward                                                                                                                                                                                                                                                                                                                                                                       | Improve Jailbreak Robustness and Safety/Security Behavior Guide Enforcement                                                           | -     | -          | -                                                         | <a href='resources_servers/jailbreak_detection/configs/jailbreak_detection_nemotron_combined_reward_tp8.yaml'>jailbreak_detection_nemotron_combined_reward_tp8.yaml</a>                                                             | -                                                                                                                                                              |
| Labbench2 Vlm                                 | knowledge             | labbench2 VLM benchmarks: scientific figure/table QA (figqa2, tableqa2), protocol troubleshooting (protocolqa2), LLM-as-judge                                                                                                                                                                                                                                                                                                   | Measure scientific reasoning on figures, tables, and lab protocols                                                                    | -     | ✓          | -                                                         | <a href='resources_servers/labbench2_vlm/configs/labbench2_vlm.yaml'>labbench2_vlm.yaml</a>                                                                                                                                         | -                                                                                                                                                              |
| Lc Niah                                       | knowledge             | Answer-correctness reward gated by low reasoning/input overlap                                                                                                                                                                                                                                                                                                                                                                  | Reward correct answers while discouraging copying the prompt into reasoning                                                           | -     | -          | -                                                         | <a href='resources_servers/lc_niah/configs/lc_niah.yaml'>lc_niah.yaml</a>                                                                                                                                                           | -                                                                                                                                                              |
| Legal Agent Bench                             | agent                 | Harbor-native integration of <a href='https://github.com/harveyai/harvey-labs/tree/f46ef86e4788545622db25dcffa3aebb7a139929'>Legal Agent Benchmark (LAB)</a>                                                                                                                                                                                                                                                                    | Improve legal-agent document review, drafting, and analysis capability                                                                | -     | ✓          | -                                                         | <a href='resources_servers/legal_agent_bench/configs/legal_agent_bench.yaml'>legal_agent_bench.yaml</a>                                                                                                                             | -                                                                                                                                                              |
| Litmus Agent                                  | knowledge             | Domain-agnostic answer verifier: extracts a model's final answer with an answer_format regex and scores it against expected_answer per an answer_type taxonomy (float, bool, string). For tool-using rows it can also host a sandbox-backed stateful Python code-execution tool.                                                                                                                                                | Reusable scoring for any benchmark whose tasks reduce to "match the expected answer".                                                 | ✓     | -          | CC-BY-SA-4.0 AND LicenseRef-OpenMDW-1.1                   | <a href='resources_servers/litmus_agent/configs/litmus_agent.yaml'>litmus_agent.yaml</a>                                                                                                                                            | <a href='https://huggingface.co/datasets/nvidia/Nemotron-RL-litmus-bench-v0.2'>Nemotron-RL-litmus-bench-v0.2</a>                                               |
| Litmus Agent                                  | knowledge             | Domain-agnostic answer verifier: extracts a model's final answer with an answer_format regex and scores it against expected_answer per an answer_type taxonomy (float, bool, string). For tool-using rows it can also host a sandbox-backed stateful Python code-execution tool. This variant backs the tool with the local Apptainer provider (no service or API key); swap to litmus_agent.yaml for the OpenSandbox provider. | Reusable scoring for any benchmark whose tasks reduce to "match the expected answer".                                                 | ✓     | -          | CC-BY-SA-4.0 AND LicenseRef-OpenMDW-1.1                   | <a href='resources_servers/litmus_agent/configs/litmus_agent_apptainer.yaml'>litmus_agent_apptainer.yaml</a>                                                                                                                        | <a href='https://huggingface.co/datasets/nvidia/Nemotron-RL-litmus-bench-v0.2'>Nemotron-RL-litmus-bench-v0.2</a>                                               |
| Long Transduction                             | other                 | Long-context transduction benchmark — model receives a long structured input and must transduce it into the expected output. Each row's `type` field selects the variant and its parser.                                                                                                                                                                                                                                        | Tests long-context fidelity on arithmetic chains, per-line UUID sorting, variable expansion, CSV permutation, and key-value lookup.   | -     | -          | -                                                         | <a href='resources_servers/long_transduction/configs/long_transduction.yaml'>long_transduction.yaml</a>                                                                                                                             | -                                                                                                                                                              |
| Longmemeval                                   | long_context          | LongMemEval long-term-memory QA (orig-session / JSON history / no-CoT) scored by an LLM judge with the upstream per-question-type rubrics.                                                                                                                                                                                                                                                                                      | Improve long-horizon memory recall, temporal reasoning, knowledge updating and abstention over multi-session chat history.            | -     | ✓          | -                                                         | <a href='resources_servers/longmemeval/configs/longmemeval.yaml'>longmemeval.yaml</a>                                                                                                                                               | -                                                                                                                                                              |
| Longmt Eval                                   | other                 | Document-level MT verifier for pg19 books using the SEGALE pipeline (ersatz segment → LASER2 embed → vecalign align → COMETKiwi score)                                                                                                                                                                                                                                                                                          | Rewards long-form book translation at the document level using reference-free COMETKiwi scores as the RL reward signal.               | -     | -          | -                                                         | <a href='resources_servers/longmt_eval/configs/longmt_pg19.yaml'>longmt_pg19.yaml</a>                                                                                                                                               | -                                                                                                                                                              |
| Longmt Eval                                   | other                 | Document-level MT verifier for wmt24pp short docs using the SEGALE pipeline (ersatz segment → LASER2 embed → vecalign align → COMETKiwi score).                                                                                                                                                                                                                                                                                 | Rewards document-level translation quality across 55 language pairs using reference-free COMETKiwi scores as the RL reward signal.    | -     | -          | -                                                         | <a href='resources_servers/longmt_eval/configs/longmt_wmt24pp.yaml'>longmt_wmt24pp.yaml</a>                                                                                                                                         | -                                                                                                                                                              |
| Longmt Eval                                   | other                 | Document-level MT verifier using the SEGALE pipeline (ersatz segment → LASER2 embed → vecalign align → COMETKiwi score)                                                                                                                                                                                                                                                                                                         | Rewards long-form translation quality at the document level using reference-free COMETKiwi scores as the RL reward signal.            | -     | -          | -                                                         | <a href='resources_servers/longmt_eval/configs/longmt_eval.yaml'>longmt_eval.yaml</a>                                                                                                                                               | -                                                                                                                                                              |
| Math Advanced Calculations                    | agent                 | An instruction following math environment with counter-intuitive calculators                                                                                                                                                                                                                                                                                                                                                    | Improve instruction following capabilities in specific math environments                                                              | ✓     | -          | Apache 2.0                                                | <a href='resources_servers/math_advanced_calculations/configs/math_advanced_calculations.yaml'>math_advanced_calculations.yaml</a>                                                                                                  | <a href='https://huggingface.co/datasets/nvidia/Nemotron-RL-math-advanced_calculations'>Nemotron-RL-math-advanced_calculations</a>                             |
| Math Formal Lean                              | math                  | Lean4 formal proof verification environment                                                                                                                                                                                                                                                                                                                                                                                     | Improve formal theorem proving capabilities                                                                                           | ✓     | -          | Apache 2.0                                                | <a href='resources_servers/math_formal_lean/configs/nemotron_clean_easy.yaml'>nemotron_clean_easy.yaml</a>                                                                                                                          | -                                                                                                                                                              |
| Math Formal Lean                              | math                  | Lean4 formal proof verification environment                                                                                                                                                                                                                                                                                                                                                                                     | Improve formal theorem proving capabilities                                                                                           | ✓     | -          | Apache 2.0                                                | <a href='resources_servers/math_formal_lean/configs/nemotron_first_try_hard.yaml'>nemotron_first_try_hard.yaml</a>                                                                                                                  | -                                                                                                                                                              |
| Math Formal Lean                              | math                  | Lean4 formal proof verification environment                                                                                                                                                                                                                                                                                                                                                                                     | Improve formal theorem proving capabilities                                                                                           | ✓     | -          | Apache 2.0                                                | <a href='resources_servers/math_formal_lean/configs/nemotron_medium_500.yaml'>nemotron_medium_500.yaml</a>                                                                                                                          | -                                                                                                                                                              |
| Math Formal Lean                              | math                  | Lean4 formal proof verification environment                                                                                                                                                                                                                                                                                                                                                                                     | Improve formal theorem proving capabilities                                                                                           | ✓     | -          | Apache 2.0                                                | <a href='resources_servers/math_formal_lean/configs/nemotron_very_easy.yaml'>nemotron_very_easy.yaml</a>                                                                                                                            | -                                                                                                                                                              |
| Math Formal Lean                              | math                  | Lean4 formal proof verification environment                                                                                                                                                                                                                                                                                                                                                                                     | Improve formal theorem proving capabilities                                                                                           | ✓     | -          | MIT                                                       | <a href='resources_servers/math_formal_lean/configs/math_formal_lean.yaml'>math_formal_lean.yaml</a>                                                                                                                                | -                                                                                                                                                              |
| Math Formal Lean                              | math                  | Lean4 formal proof verification environment with multi-turn self-correction                                                                                                                                                                                                                                                                                                                                                     | Improve formal theorem proving capabilities                                                                                           | ✓     | -          | MIT                                                       | <a href='resources_servers/math_formal_lean/configs/math_formal_lean_multi_turn.yaml'>math_formal_lean_multi_turn.yaml</a>                                                                                                          | -                                                                                                                                                              |
| Math Proof Judgement                          | math                  | Binary judgement of math proofs — the policy model reads a problem plus a candidate proof and outputs Judgement: Yes/No.                                                                                                                                                                                                                                                                                                        | Improve the NVIDIA ProofBench judge benchmark and math-proof verification skill.                                                      | -     | -          | -                                                         | <a href='resources_servers/math_proof_judgement/configs/math_proof_judgement.yaml'>math_proof_judgement.yaml</a>                                                                                                                    | -                                                                                                                                                              |
| Math With Autograder                          | math                  | Math QA verified by a Skills-style autograder LLM judge with math-verify symbolic fallback                                                                                                                                                                                                                                                                                                                                      | Score hard-math benchmarks (e.g. IMO AnswerBench) where the judge is a unidirectional Correct/Incorrect grader                        | -     | -          | -                                                         | <a href='resources_servers/math_with_autograder/configs/math_with_autograder.yaml'>math_with_autograder.yaml</a>                                                                                                                    | -                                                                                                                                                              |
| Math With Code                                | math                  | Model solves competitive math problems using simple calculator tools                                                                                                                                                                                                                                                                                                                                                            | Improve math and simple tool use capabilities                                                                                         | ✓     | -          | Apache 2.0                                                | <a href='resources_servers/math_with_code/configs/math_with_code.yaml'>math_with_code.yaml</a>                                                                                                                                      | -                                                                                                                                                              |
| Math With Judge                               | math                  | DAPO17k math dataset with math-verify                                                                                                                                                                                                                                                                                                                                                                                           | Improve math capabilities including AIME 24 / 25                                                                                      | ✓     | ✓          | Apache 2.0                                                | <a href='resources_servers/math_with_judge/configs/dapo17k.yaml'>dapo17k.yaml</a>                                                                                                                                                   | -                                                                                                                                                              |
| Math With Judge                               | math                  | DAPO17k train problems repeated for trajectory collection with math-verify                                                                                                                                                                                                                                                                                                                                                      | Collect rollouts on DAPO17k without training (NeMo RL is_trajectory_collection)                                                       | -     | ✓          | -                                                         | <a href='resources_servers/math_with_judge/configs/dapo17k_trajectory_collection.yaml'>dapo17k_trajectory_collection.yaml</a>                                                                                                       | -                                                                                                                                                              |
| Math With Judge                               | math                  | MathStackOverflow math dataset with math-verify                                                                                                                                                                                                                                                                                                                                                                                 | Improve math capabilities including AIME 24 / 25                                                                                      | ✓     | ✓          | Creative Commons Attribution-ShareAlike 4.0 International | <a href='resources_servers/math_with_judge/configs/math_stack_overflow.yaml'>math_stack_overflow.yaml</a>                                                                                                                           | <a href='https://huggingface.co/datasets/nvidia/Nemotron-RL-math-stack_overflow'>Nemotron-RL-math-stack_overflow</a>                                           |
| Math With Judge                               | math                  | OpenMathReasoning math dataset with math-verify and LLM-as-a-judge                                                                                                                                                                                                                                                                                                                                                              | Improve math capabilities including AIME 24 / 25                                                                                      | ✓     | ✓          | Creative Commons Attribution 4.0 International            | <a href='resources_servers/math_with_judge/configs/math_with_judge.yaml'>math_with_judge.yaml</a>                                                                                                                                   | <a href='https://huggingface.co/datasets/nvidia/Nemotron-RL-math-OpenMathReasoning'>Nemotron-RL-math-OpenMathReasoning</a>                                     |
| Mcqa                                          | knowledge             | Multi-choice question answering problems                                                                                                                                                                                                                                                                                                                                                                                        | Improve benchmarks like MMLU / GPQA / HLE                                                                                             | ✓     | ✓          | Apache 2.0                                                | <a href='resources_servers/mcqa/configs/mcqa.yaml'>mcqa.yaml</a>                                                                                                                                                                    | <a href='https://huggingface.co/datasets/nvidia/Nemotron-RL-knowledge-mcqa'>Nemotron-RL-knowledge-mcqa</a>                                                     |
| Mimo Music                                    | other                 | Single-turn ABC music composition using the released MiMo music scorer.                                                                                                                                                                                                                                                                                                                                                         | Graded symbolic-music rewards from MIDI features without an LLM judge.                                                                | -     | -          | -                                                         | <a href='resources_servers/mimo_music/configs/mimo_music.yaml'>mimo_music.yaml</a>                                                                                                                                                  | -                                                                                                                                                              |
| Mini Swe Agent                                | coding                | Software engineering tasks driven by mini-swe agent harness.                                                                                                                                                                                                                                                                                                                                                                    | Improve agentic software engineering capabilities.                                                                                    | ✓     | ✓          | MIT                                                       | <a href='responses_api_agents/mini_swe_agent/configs/mini_swe_agent.yaml'>mini_swe_agent.yaml</a>                                                                                                                                   | <a href='https://huggingface.co/datasets/SWE-Gym/SWE-Gym'>SWE-Gym</a>                                                                                          |
| Moldetox                                      | knowledge             | MolDeTox toxicity-aware molecular editing verifier                                                                                                                                                                                                                                                                                                                                                                              | Evaluate toxicity-aware molecular editing with the MolDeTox benchmark                                                                 | -     | ✓          | -                                                         | <a href='resources_servers/moldetox/configs/moldetox.yaml'>moldetox.yaml</a>                                                                                                                                                        | -                                                                                                                                                              |
| Mrcr                                          | other                 | Multi-round coreference resolution over multi-turn conversations with prefix-gated SequenceMatcher grading                                                                                                                                                                                                                                                                                                                      | Improve long-context in-context retrieval and needle-count-aware reasoning                                                            | -     | -          | -                                                         | <a href='resources_servers/mrcr/configs/mrcr.yaml'>mrcr.yaml</a>                                                                                                                                                                    | -                                                                                                                                                              |
| Multichallenge                                | knowledge             | Targets inference memory, instruction retention, version editing, and self-coherence.                                                                                                                                                                                                                                                                                                                                           | Improve complex multi-turn conversational capability                                                                                  | ✓     | -          | Creative Commons Attribution 4.0 International            | <a href='resources_servers/multichallenge/configs/multichallenge_nrl.yaml'>multichallenge_nrl.yaml</a>                                                                                                                              | <a href='https://huggingface.co/datasets/nvidia/Nemotron-RL-Instruction-Following-MultiTurnChat-v1'>Nemotron-RL-Instruction-Following-MultiTurnChat-v1</a>     |
| Newton Bench                                  | math                  | Scientific law discovery tasks through agentic experimentation across 12 physics domains                                                                                                                                                                                                                                                                                                                                        | Improve science, reasoning, and tool use capabilities                                                                                 | ✓     | -          | Apache 2.0                                                | <a href='resources_servers/newton_bench/configs/newton_bench.yaml'>newton_bench.yaml</a>                                                                                                                                            | -                                                                                                                                                              |
| Ns Tools                                      | agent                 | NeMo Skills tool execution with math verification                                                                                                                                                                                                                                                                                                                                                                               | -                                                                                                                                     | -     | -          | -                                                         | <a href='resources_servers/ns_tools/configs/ns_tools.yaml'>ns_tools.yaml</a>                                                                                                                                                        | -                                                                                                                                                              |
| Nullable Tool Args                            | agent                 | Required nullable tool arguments must be JSON null, not the string "None"                                                                                                                                                                                                                                                                                                                                                       | -                                                                                                                                     | -     | -          | -                                                         | <a href='resources_servers/nullable_tool_args/configs/nullable_tool_args.yaml'>nullable_tool_args.yaml</a>                                                                                                                          | -                                                                                                                                                              |
| Nvarc                                         | knowledge             | ARC-AGI inductive mode: model outputs Python code with transform()                                                                                                                                                                                                                                                                                                                                                              | Improve ARC-AGI puzzle-solving by inducing executable transformation programs                                                         | ✓     | ✓          | Apache 2.0                                                | <a href='resources_servers/nvarc/configs/inductive.yaml'>inductive.yaml</a>                                                                                                                                                         | -                                                                                                                                                              |
| Nvarc                                         | knowledge             | ARC-AGI transductive mode: model outputs grid directly                                                                                                                                                                                                                                                                                                                                                                          | Improve ARC-AGI puzzle-solving by directly predicting transformed grids                                                               | ✓     | ✓          | Apache 2.0                                                | <a href='resources_servers/nvarc/configs/transductive.yaml'>transductive.yaml</a>                                                                                                                                                   | -                                                                                                                                                              |
| Omniscience                                   | knowledge             | Omniscience factual knowledge QA with LLM judge verification                                                                                                                                                                                                                                                                                                                                                                    | Evaluate factual recall and calibration via LLM-graded open-ended QA                                                                  | -     | -          | -                                                         | <a href='resources_servers/omniscience/configs/omniscience.yaml'>omniscience.yaml</a>                                                                                                                                               | -                                                                                                                                                              |
| Openair Congestion                            | agent                 | Multi-turn 5G congestion control with deterministic synthetic dynamics, Gymnasium API style. The agent observes rolling 5G KPIs each step and issues exactly one network-control tool call (7 actuators + noop). Dense per-step KPI reward; the agent sums step rewards into the episode return. No live OAI/FlexRIC backend is included.                                                                                       | Stateful multi-turn telco control env (replay backend, no 5G lab/GPU).                                                                | -     | -          | -                                                         | <a href='resources_servers/openair_congestion/configs/openair_congestion.yaml'>openair_congestion.yaml</a>                                                                                                                          | -                                                                                                                                                              |
| Opencode Search                               |                       | -                                                                                                                                                                                                                                                                                                                                                                                                                               | -                                                                                                                                     | -     | -          | -                                                         | <a href='resources_servers/opencode_search/configs/opencode_search_example.yaml'>opencode_search_example.yaml</a>                                                                                                                   | -                                                                                                                                                              |
| Openenv                                       | agent                 | Echo environment via OpenEnv (MCP). Echoes messages back with length-based rewards.                                                                                                                                                                                                                                                                                                                                             | -                                                                                                                                     | -     | -          | -                                                         | <a href='resources_servers/openenv/configs/openenv_echo.yaml'>openenv_echo.yaml</a>                                                                                                                                                 | -                                                                                                                                                              |
| Openenv                                       | coding                | Python code execution environment via OpenEnv. Executes code and returns stdout/stderr.                                                                                                                                                                                                                                                                                                                                         | -                                                                                                                                     | -     | -          | -                                                         | <a href='resources_servers/openenv/configs/openenv_coding.yaml'>openenv_coding.yaml</a>                                                                                                                                             | -                                                                                                                                                              |
| Openenv                                       | games                 | Maze navigation environment via OpenEnv. Agent navigates an 8x8 grid to find the exit.                                                                                                                                                                                                                                                                                                                                          | -                                                                                                                                     | -     | -          | -                                                         | <a href='resources_servers/openenv/configs/openenv_maze.yaml'>openenv_maze.yaml</a>                                                                                                                                                 | -                                                                                                                                                              |
| Osworld Agent                                 | agent                 | Real desktop-computer tasks driven by the OSWorld harness (DesktopEnv + inline evaluator).                                                                                                                                                                                                                                                                                                                                      | Improve agentic computer-use capabilities (GUI navigation, multi-app workflows, OS-level operations).                                 | ✓     | ✓          | Apache 2.0                                                | <a href='benchmarks/osworld/config.yaml'>config.yaml</a>                                                                                                                                                                            | <a href='https://huggingface.co/datasets/xlangai/osworld'>osworld</a>                                                                                          |
| Over Refusal Detection                        |                       | -                                                                                                                                                                                                                                                                                                                                                                                                                               | -                                                                                                                                     | ✓     | -          | TBD                                                       | <a href='resources_servers/over_refusal_detection/configs/over_refusal_detection.yaml'>over_refusal_detection.yaml</a>                                                                                                              | -                                                                                                                                                              |
| Partner If                                    | instruction_following | Mock-tool variant that grades live tool-calling episodes against instruction-following rubrics, with an example notes backend.                                                                                                                                                                                                                                                                                                  | -                                                                                                                                     | -     | -          | -                                                         | <a href='resources_servers/partner_if/configs/mock_tools.yaml'>mock_tools.yaml</a>                                                                                                                                                  | -                                                                                                                                                              |
| Partner If                                    | instruction_following | Text variant that grades a response and its visible evidence against versioned instruction-following rubrics.                                                                                                                                                                                                                                                                                                                   | -                                                                                                                                     | -     | -          | -                                                         | <a href='resources_servers/partner_if/configs/partner_if.yaml'>partner_if.yaml</a>                                                                                                                                                  | -                                                                                                                                                              |
| Physics Judge                                 | math                  | Physics QA verified by NeMo Skills' physics judge LLM with math-verify symbolic fallback                                                                                                                                                                                                                                                                                                                                        | Score open-ended physics benchmarks (e.g. PHYSICS) where the judge emits [Correct] / [Incorrect] verdicts                             | -     | -          | -                                                         | <a href='resources_servers/physics_judge/configs/physics_judge.yaml'>physics_judge.yaml</a>                                                                                                                                         | -                                                                                                                                                              |
| Pinchbench                                    | agent                 | PinchBench benchmark integration                                                                                                                                                                                                                                                                                                                                                                                                | Evaluate a model as the brain of an OpenClaw agent on real-world tasks.                                                               | -     | -          | -                                                         | <a href='responses_api_agents/pinchbench/configs/pinchbench.yaml'>pinchbench.yaml</a>                                                                                                                                               | -                                                                                                                                                              |
| Polymath                                      | math                  | PolyMath multilingual math benchmark with weighted (difficulty) and per-language metrics                                                                                                                                                                                                                                                                                                                                        | Improve multilingual math reasoning across 18 languages and 4 difficulty tiers                                                        | -     | -          | -                                                         | <a href='resources_servers/polymath/configs/polymath.yaml'>polymath.yaml</a>                                                                                                                                                        | -                                                                                                                                                              |
| Proof Genselect                               | math                  | Pairwise proof selection with binary correctness reward                                                                                                                                                                                                                                                                                                                                                                         | -                                                                                                                                     | -     | -          | -                                                         | <a href='resources_servers/proof_genselect/configs/proof_genselect.yaml'>proof_genselect.yaml</a>                                                                                                                                   | -                                                                                                                                                              |
| Proof Judge                                   | math                  | Theorem proving with verifier + meta-verifier judge (combined env)                                                                                                                                                                                                                                                                                                                                                              | -                                                                                                                                     | -     | -          | -                                                         | <a href='resources_servers/proof_judge/configs/proof_judge.yaml'>proof_judge.yaml</a>                                                                                                                                               | -                                                                                                                                                              |
| Proof Jury Judge                              | math                  | Reference-free IMO proof grading (0-7) by a jury of three frontier LLM judges                                                                                                                                                                                                                                                                                                                                                   | Measure natural-language olympiad proof quality without reference solutions                                                           | -     | -          | -                                                         | <a href='resources_servers/proof_jury_judge/configs/proof_jury_judge.yaml'>proof_jury_judge.yaml</a>                                                                                                                                | -                                                                                                                                                              |
| Proof Verification                            | math                  | Proof verification scored against ground truth and meta-verifier agreement                                                                                                                                                                                                                                                                                                                                                      | -                                                                                                                                     | -     | -          | -                                                         | <a href='resources_servers/proof_verification/configs/proof_verification.yaml'>proof_verification.yaml</a>                                                                                                                          | -                                                                                                                                                              |
| R2E Gym                                       |                       | -                                                                                                                                                                                                                                                                                                                                                                                                                               | -                                                                                                                                     | -     | -          | -                                                         | <a href='resources_servers/r2e_gym/configs/r2e_gym_example.yaml'>r2e_gym_example.yaml</a>                                                                                                                                           | -                                                                                                                                                              |
| R2E Gym                                       |                       | -                                                                                                                                                                                                                                                                                                                                                                                                                               | -                                                                                                                                     | ✓     | -          | MIT (R2E-Gym project license; dataset card unspecified)   | <a href='resources_servers/r2e_gym/configs/r2e_gym_opencode.yaml'>r2e_gym_opencode.yaml</a>                                                                                                                                         | -                                                                                                                                                              |
| Ragtruth                                      | knowledge             | RAGTruth case-level hallucination detection; reward = 1 when the model's binary "any hallucination?" verdict matches the gold label.                                                                                                                                                                                                                                                                                            | Improve faithfulness and grounding of generated text against supplied context.                                                        | -     | ✓          | -                                                         | <a href='resources_servers/ragtruth/configs/ragtruth.yaml'>ragtruth.yaml</a>                                                                                                                                                        | -                                                                                                                                                              |
| Reasoning Gym                                 | knowledge             | Claude Code agent harness for reasoning gym tasks                                                                                                                                                                                                                                                                                                                                                                               | Evaluate model capabilities in the Claude Code agent harness                                                                          | ✓     | -          | Creative Commons Attribution 4.0 International            | <a href='resources_servers/reasoning_gym/configs/reasoning_gym_claude_code_agent.yaml'>reasoning_gym_claude_code_agent.yaml</a>                                                                                                     | <a href='https://huggingface.co/datasets/nvidia/Nemotron-RL-ReasoningGym-v1'>Nemotron-RL-ReasoningGym-v1</a>                                                   |
| Reasoning Gym                                 | knowledge             | Claude Code agent harness for reasoning gym tasks, via a Gym model server's /v1/messages                                                                                                                                                                                                                                                                                                                                        | Showcase Claude Code running against any Gym model backend                                                                            | -     | -          | -                                                         | <a href='resources_servers/reasoning_gym/configs/reasoning_gym_claude_code_agent_model_server.yaml'>reasoning_gym_claude_code_agent_model_server.yaml</a>                                                                           | -                                                                                                                                                              |
| Reasoning Gym                                 | knowledge             | Codex agent harness for reasoning gym tasks                                                                                                                                                                                                                                                                                                                                                                                     | Evaluate model capabilities in the Codex agent harness                                                                                | -     | -          | -                                                         | <a href='resources_servers/reasoning_gym/configs/reasoning_gym_codex_agent.yaml'>reasoning_gym_codex_agent.yaml</a>                                                                                                                 | -                                                                                                                                                              |
| Reasoning Gym                                 | knowledge             | Codex agent harness for reasoning gym tasks, via a Gym model server's /v1/responses                                                                                                                                                                                                                                                                                                                                             | Showcase Codex running against any Gym model backend                                                                                  | -     | -          | -                                                         | <a href='resources_servers/reasoning_gym/configs/reasoning_gym_codex_agent_model_server.yaml'>reasoning_gym_codex_agent_model_server.yaml</a>                                                                                       | -                                                                                                                                                              |
| Reasoning Gym                                 | knowledge             | LangGraph orchestrator agent compatible with resource servers that do not use tools; enables diverse agent training data and test time scaling vs a simple agent, extensible to use tools or other agent architectures                                                                                                                                                                                                          | Iterative test time scaling for improved performance in reasoning tasks                                                               | ✓     | -          | Apache 2.0                                                | <a href='resources_servers/reasoning_gym/configs/orchestrator_agent.yaml'>orchestrator_agent.yaml</a>                                                                                                                               | -                                                                                                                                                              |
| Reasoning Gym                                 | knowledge             | LangGraph parallel thinking agent compatible with resource servers that do not use tools; enables diverse agent training data and test time scaling vs a simple agent, extensible to use tools or other agent architectures                                                                                                                                                                                                     | Iterative test time scaling for improved performance in reasoning tasks                                                               | ✓     | -          | Apache 2.0                                                | <a href='resources_servers/reasoning_gym/configs/parallel_thinking_agent.yaml'>parallel_thinking_agent.yaml</a>                                                                                                                     | -                                                                                                                                                              |
| Reasoning Gym                                 | knowledge             | LangGraph reflection agent compatible with resource servers that do not use tools; provides iterative reflection for diverse agent training data and test time scaling, extensible to use tools or other agent architectures                                                                                                                                                                                                    | Iterative test time scaling for improved performance in reasoning tasks                                                               | ✓     | -          | Apache 2.0                                                | <a href='resources_servers/reasoning_gym/configs/reflection_agent.yaml'>reflection_agent.yaml</a>                                                                                                                                   | -                                                                                                                                                              |
| Reasoning Gym                                 | knowledge             | LangGraph ReWOO agent compatible with resource servers that do not use tools; enables diverse agent training data and test time scaling vs a simple agent, extensible to use tools or other agent architectures                                                                                                                                                                                                                 | Iterative test time scaling for improved performance in reasoning tasks                                                               | ✓     | -          | Apache 2.0                                                | <a href='resources_servers/reasoning_gym/configs/rewoo_agent.yaml'>rewoo_agent.yaml</a>                                                                                                                                             | -                                                                                                                                                              |
| Reasoning Gym                                 | knowledge             | Over 100 tasks including algebra, arithmetic, computation, cognition, geometry, graph theory, logic, and many common games.                                                                                                                                                                                                                                                                                                     | Improve robustness, generalization, broad knowledge and reasoning                                                                     | ✓     | -          | Creative Commons Attribution 4.0 International            | <a href='resources_servers/reasoning_gym/configs/reasoning_gym.yaml'>reasoning_gym.yaml</a>                                                                                                                                         | <a href='https://huggingface.co/datasets/nvidia/Nemotron-RL-ReasoningGym-v1'>Nemotron-RL-ReasoningGym-v1</a>                                                   |
| Rna Design                                    | agent                 | RNA inverse folding: the design tools served over MCP to a harness such as Claude Code.                                                                                                                                                                                                                                                                                                                                         | -                                                                                                                                     | -     | -          | -                                                         | <a href='resources_servers/rna_design/configs/rna_design.yaml'>rna_design.yaml</a>                                                                                                                                                  | -                                                                                                                                                              |
| Rolemrc                                       | instruction_following | RoleMRC role-play MRC scored with reference metrics (ROUGE/BLEU/METEOR/BERTScore); ROUGE-L is the reward.                                                                                                                                                                                                                                                                                                                       | Improve role-play instruction following and knowledge-grounded responses.                                                             | -     | ✓          | -                                                         | <a href='resources_servers/rolemrc/configs/rolemrc.yaml'>rolemrc.yaml</a>                                                                                                                                                           | -                                                                                                                                                              |
| Rolemrc                                       | rlhf                  | RoleMRC role-play MRC scored by a 5-aspect LLM-as-judge (knowledge range, style, nested/multi-turn instruction, instruction priority).                                                                                                                                                                                                                                                                                          | Improve role-play instruction following under knowledge-range and instruction-priority constraints.                                   | -     | ✓          | -                                                         | <a href='resources_servers/rolemrc/configs/rolemrc_judge.yaml'>rolemrc_judge.yaml</a>                                                                                                                                               | -                                                                                                                                                              |
| Ruler                                         | other                 | -                                                                                                                                                                                                                                                                                                                                                                                                                               | -                                                                                                                                     | -     | -          | -                                                         | <a href='resources_servers/ruler/configs/ruler.yaml'>ruler.yaml</a>                                                                                                                                                                 | -                                                                                                                                                              |
| Ruler2                                        | other                 | Long-context RULER v2 verifier with WER-fallback soft string match across 3 match types plus a multichoice route                                                                                                                                                                                                                                                                                                                | Improve long-context retrieval, multi-key/multi-value needle search, and document-grounded QA                                         | -     | -          | -                                                         | <a href='resources_servers/ruler2/configs/ruler2.yaml'>ruler2.yaml</a>                                                                                                                                                              | -                                                                                                                                                              |
| Scale Swe                                     |                       | -                                                                                                                                                                                                                                                                                                                                                                                                                               | -                                                                                                                                     | -     | -          | -                                                         | <a href='resources_servers/scale_swe/configs/scale_swe_example.yaml'>scale_swe_example.yaml</a>                                                                                                                                     | -                                                                                                                                                              |
| Scale Swe                                     |                       | -                                                                                                                                                                                                                                                                                                                                                                                                                               | -                                                                                                                                     | ✓     | -          | TBD                                                       | <a href='resources_servers/scale_swe/configs/scale_swe_opencode.yaml'>scale_swe_opencode.yaml</a>                                                                                                                                   | -                                                                                                                                                              |
| Scicode                                       | coding                | Multi-step scientific code generation; sub-step solutions executed against SciCode test cases                                                                                                                                                                                                                                                                                                                                   | Improve multi-step scientific code generation                                                                                         | -     | -          | -                                                         | <a href='resources_servers/scicode/configs/scicode.yaml'>scicode.yaml</a>                                                                                                                                                           | -                                                                                                                                                              |
| Scicodepile                                   | coding                | Verifies model-generated Python against SciCodePile's runnable scientific-code tests.                                                                                                                                                                                                                                                                                                                                           | Improve scientific and research code generation grounded in real computational-science repositories.                                  | -     | -          | -                                                         | <a href='resources_servers/scicodepile/configs/scicodepile.yaml'>scicodepile.yaml</a>                                                                                                                                               | -                                                                                                                                                              |
| Simpleqa                                      | knowledge             | SimpleQA short-form factual QA with 3-tier LLM judge (CORRECT / INCORRECT / NOT_ATTEMPTED)                                                                                                                                                                                                                                                                                                                                      | Evaluate factual recall and abstention calibration via LLM-graded open-ended QA                                                       | -     | -          | -                                                         | <a href='resources_servers/simpleqa/configs/simpleqa.yaml'>simpleqa.yaml</a>                                                                                                                                                        | -                                                                                                                                                              |
| Single Step Tool Use With Argument Comparison | agent                 | BrowseComp-style single-step verifier for search-agent trajectories. Search queries must match the golden word bag exactly, list arguments use strong list-F1 guardrails, browse URLs must match exactly, and bash_command / update_progress score on tool name alone. A response with more than one tool call scores 0.                                                                                                        | Exact-match search queries for reward profiling, eliminating partial-credit reward hacking.                                           | ✓     | ✓          | Apache 2.0                                                | <a href='resources_servers/single_step_tool_use_with_argument_comparison/configs/bc_v4_8.yaml'>bc_v4_8.yaml</a>                                                                                                                     | -                                                                                                                                                              |
| Single Step Tool Use With Argument Comparison | agent                 | Conversational tool-use RL from expert trajectories; behavior cloning per step across auth, lookup, and servicing domains.                                                                                                                                                                                                                                                                                                      | -                                                                                                                                     | ✓     | ✓          | Creative Commons Attribution 4.0 International            | <a href='resources_servers/single_step_tool_use_with_argument_comparison/configs/single_step_tool_use_with_argument_comparison.yaml'>single_step_tool_use_with_argument_comparison.yaml</a>                                         | <a href='https://huggingface.co/datasets/nvidia/Nemotron-RL-Agentic-Conversational-Tool-Use-Pivot-v1'>Nemotron-RL-Agentic-Conversational-Tool-Use-Pivot-v1</a> |
| Single Step Tool Use With Argument Comparison | agent                 | Droid agent pivot dataset; behavior cloning per step from successful Droid rollouts.                                                                                                                                                                                                                                                                                                                                            | -                                                                                                                                     | -     | -          | -                                                         | <a href='resources_servers/single_step_tool_use_with_argument_comparison/configs/droid_pivot_single_step_tool_use_with_argument_comparison.yaml'>droid_pivot_single_step_tool_use_with_argument_comparison.yaml</a>                 | -                                                                                                                                                              |
| Single Step Tool Use With Argument Comparison | agent                 | General function-calling RL dataset using expert trajectories; behavior cloning to match expert tool calls per step.                                                                                                                                                                                                                                                                                                            | -                                                                                                                                     | ✓     | ✓          | Creative Commons Attribution 4.0 International            | <a href='resources_servers/single_step_tool_use_with_argument_comparison/configs/toolcall_schema_single_step_tool_use_with_argument_comparison.yaml'>toolcall_schema_single_step_tool_use_with_argument_comparison.yaml</a>         | <a href='https://huggingface.co/datasets/nvidia/Nemotron-RL-Agentic-Function-Calling-Pivot-v1'>Nemotron-RL-Agentic-Function-Calling-Pivot-v1</a>               |
| Single Step Tool Use With Argument Comparison | agent                 | GitHub-issue dataset for software-engineering agents; refactored from SWE-Gym and SWE-Bench-Verified for NeMo Gym.                                                                                                                                                                                                                                                                                                              | -                                                                                                                                     | ✓     | ✓          | Creative Commons Attribution 4.0 International            | <a href='resources_servers/single_step_tool_use_with_argument_comparison/configs/swe_pivot_single_step_tool_use_with_argument_comparison.yaml'>swe_pivot_single_step_tool_use_with_argument_comparison.yaml</a>                     | <a href='https://huggingface.co/datasets/nvidia/Nemotron-RL-Agentic-SWE-Pivot-v1'>Nemotron-RL-Agentic-SWE-Pivot-v1</a>                                         |
| Single Step Tool Use With Argument Comparison | agent                 | Parallel tool-call verification; the model must emit the expected set of tool calls in a single turn, in any order.                                                                                                                                                                                                                                                                                                             | -                                                                                                                                     | -     | -          | -                                                         | <a href='resources_servers/single_step_tool_use_with_argument_comparison/configs/parallel_tool_calls_single_step_tool_use_with_argument_comparison.yaml'>parallel_tool_calls_single_step_tool_use_with_argument_comparison.yaml</a> | -                                                                                                                                                              |
| Single Step Tool Use With Argument Comparison | agent                 | The model must output the next correct call in a given trajectory involving search tools.                                                                                                                                                                                                                                                                                                                                       | Improve agentic search capability.                                                                                                    | ✓     | ✓          | Apache 2.0                                                | <a href='resources_servers/single_step_tool_use_with_argument_comparison/configs/search_pivot_single_step_tool_use_with_argument_comparison.yaml'>search_pivot_single_step_tool_use_with_argument_comparison.yaml</a>               | -                                                                                                                                                              |
| Spartqa                                       | other                 | SpartQA spatial reasoning, CO (choose-object) question type; four candidate answers per question (two story objects, "both of them", "none of them"); reward = 1 iff the answer resolves to the single gold label.                                                                                                                                                                                                              | Improve spatial and relational reasoning over described scenes.                                                                       | -     | ✓          | -                                                         | <a href='resources_servers/spartqa/configs/spartqa.yaml'>spartqa.yaml</a>                                                                                                                                                           | -                                                                                                                                                              |
| Speed Bench                                   | other                 | Speculative-decoding throughput benchmark. Aggregates vLLM per-request acceptance metrics returned by the agent.                                                                                                                                                                                                                                                                                                                | Measure inference-time speculative-decoding effectiveness for serving research and regression tests.                                  | -     | -          | -                                                         | <a href='resources_servers/speed_bench/configs/speed_bench.yaml'>speed_bench.yaml</a>                                                                                                                                               | -                                                                                                                                                              |
| Spider2 Lite                                  | coding                | Text-to-SQL with execution-based evaluation on Spider 2.0-Lite (135 SQLite tasks). Binary reward based on result-set equivalence.                                                                                                                                                                                                                                                                                               | Improve text-to-SQL capabilities for real-world enterprise queries using execution-based binary reward without an LLM judge.          | -     | ✓          | -                                                         | <a href='resources_servers/spider2_lite/configs/spider2_lite.yaml'>spider2_lite.yaml</a>                                                                                                                                            | -                                                                                                                                                              |
| String Match                                  | knowledge             | General-purpose string matching verifier for free-form text answers                                                                                                                                                                                                                                                                                                                                                             | Verify answers via case-insensitive string matching with multiple extraction strategies                                               | -     | -          | -                                                         | <a href='resources_servers/string_match/configs/string_match.yaml'>string_match.yaml</a>                                                                                                                                            | -                                                                                                                                                              |
| Structeval                                    | instruction_following | StructEval non-renderable format verification (JSON, YAML, CSV, TOML, XML)                                                                                                                                                                                                                                                                                                                                                      | Improve structured output generation quality                                                                                          | ✓     | -          | Apache 2.0                                                | <a href='resources_servers/structeval/configs/structeval_nonrenderable.yaml'>structeval_nonrenderable.yaml</a>                                                                                                                      | -                                                                                                                                                              |
| Structured Outputs                            | instruction_following | Check if responses are following structured output requirements in prompts                                                                                                                                                                                                                                                                                                                                                      | Improve instruction following capabilities                                                                                            | ✓     | ✓          | Apache 2.0                                                | <a href='resources_servers/structured_outputs/configs/structured_outputs_json.yaml'>structured_outputs_json.yaml</a>                                                                                                                | <a href='https://huggingface.co/datasets/nvidia/Nemotron-RL-instruction_following-structured_outputs'>Nemotron-RL-instruction_following-structured_outputs</a> |
| Structured Outputs                            | instruction_following | Check if responses are following structured output requirements in prompts                                                                                                                                                                                                                                                                                                                                                      | Improve instruction following capabilities                                                                                            | ✓     | ✓          | Apache 2.0                                                | <a href='resources_servers/structured_outputs/configs/structured_outputs_json_yaml_xml_v1.yaml'>structured_outputs_json_yaml_xml_v1.yaml</a>                                                                                        | -                                                                                                                                                              |
| Structured Outputs                            | instruction_following | Check if responses follow structured output requirements (JSON, YAML, XML, TOML, CSV). Created 20260409.                                                                                                                                                                                                                                                                                                                        | Improve schema adherence across all structured output formats                                                                         | ✓     | -          | Apache 2.0                                                | <a href='resources_servers/structured_outputs/configs/structured_outputs_v3.yaml'>structured_outputs_v3.yaml</a>                                                                                                                    | -                                                                                                                                                              |
| Structured Outputs                            | instruction_following | Check if responses follow tool-call structured output schemas. Created 20260424.                                                                                                                                                                                                                                                                                                                                                | Improve schema adherence when structured output is expressed through tool calls                                                       | ✓     | -          | Apache 2.0                                                | <a href='resources_servers/structured_outputs/configs/structured_outputs_v4.yaml'>structured_outputs_v4.yaml</a>                                                                                                                    | -                                                                                                                                                              |
| Swe Agents                                    |                       | -                                                                                                                                                                                                                                                                                                                                                                                                                               | -                                                                                                                                     | ✓     | ✓          | Apache 2.0                                                | <a href='responses_api_agents/swe_agents/configs/swebench_multi_tools.yaml'>swebench_multi_tools.yaml</a>                                                                                                                           | -                                                                                                                                                              |
| Swe Agents                                    |                       | -                                                                                                                                                                                                                                                                                                                                                                                                                               | -                                                                                                                                     | ✓     | ✓          | Apache 2.0                                                | <a href='responses_api_agents/swe_agents/configs/swebench_openhands.yaml'>swebench_openhands.yaml</a>                                                                                                                               | -                                                                                                                                                              |
| Swe Agents                                    |                       | -                                                                                                                                                                                                                                                                                                                                                                                                                               | -                                                                                                                                     | ✓     | ✓          | Apache 2.0                                                | <a href='responses_api_agents/swe_agents/configs/swebench_openhands_training.yaml'>swebench_openhands_training.yaml</a>                                                                                                             | -                                                                                                                                                              |
| Swe Agents                                    | coding                | SWE-bench driven by the opencode agent framework for RL training.                                                                                                                                                                                                                                                                                                                                                               | Train software engineering capabilities on SWE tasks using opencode rollouts.                                                         | ✓     | -          | Apache 2.0                                                | <a href='responses_api_agents/swe_agents/configs/swebench_opencode_training.yaml'>swebench_opencode_training.yaml</a>                                                                                                               | -                                                                                                                                                              |
| Swe Agents                                    | coding                | SWE-bench driven by the opencode agent framework.                                                                                                                                                                                                                                                                                                                                                                               | Eval software engineering capabilities on SWE-bench using opencode.                                                                   | ✓     | ✓          | Apache 2.0                                                | <a href='responses_api_agents/swe_agents/configs/swebench_opencode.yaml'>swebench_opencode.yaml</a>                                                                                                                                 | -                                                                                                                                                              |
| Swe Atlas Qa                                  | coding                | SWE Atlas Codebase Q&A with the upstream rubric evaluator                                                                                                                                                                                                                                                                                                                                                                       | -                                                                                                                                     | -     | -          | -                                                         | <a href='resources_servers/swe_atlas_qa/configs/swe_atlas_qa.yaml'>swe_atlas_qa.yaml</a>                                                                                                                                            | -                                                                                                                                                              |
| Swe Gym                                       |                       | -                                                                                                                                                                                                                                                                                                                                                                                                                               | -                                                                                                                                     | -     | -          | -                                                         | <a href='resources_servers/swe_gym/configs/swe_gym_example.yaml'>swe_gym_example.yaml</a>                                                                                                                                           | -                                                                                                                                                              |
| Swe Gym                                       |                       | -                                                                                                                                                                                                                                                                                                                                                                                                                               | -                                                                                                                                     | ✓     | -          | MIT                                                       | <a href='resources_servers/swe_gym/configs/swe_gym_opencode.yaml'>swe_gym_opencode.yaml</a>                                                                                                                                         | -                                                                                                                                                              |
| Swe Internal V1                               |                       | -                                                                                                                                                                                                                                                                                                                                                                                                                               | -                                                                                                                                     | -     | -          | -                                                         | <a href='resources_servers/swe_internal_v1/configs/swe_internal_v1_example.yaml'>swe_internal_v1_example.yaml</a>                                                                                                                   | -                                                                                                                                                              |
| Swe Internal V1                               |                       | -                                                                                                                                                                                                                                                                                                                                                                                                                               | -                                                                                                                                     | ✓     | -          | NVIDIA Internal Use Only, Do Not Distribute               | <a href='resources_servers/swe_internal_v1/configs/swe_internal_v1_opencode.yaml'>swe_internal_v1_opencode.yaml</a>                                                                                                                 | -                                                                                                                                                              |
| Swe Next                                      |                       | -                                                                                                                                                                                                                                                                                                                                                                                                                               | -                                                                                                                                     | -     | -          | -                                                         | <a href='resources_servers/swe_next/configs/swe_next_example.yaml'>swe_next_example.yaml</a>                                                                                                                                        | -                                                                                                                                                              |
| Swe Next                                      |                       | -                                                                                                                                                                                                                                                                                                                                                                                                                               | -                                                                                                                                     | ✓     | -          | MIT                                                       | <a href='resources_servers/swe_next/configs/swe_next_opencode.yaml'>swe_next_opencode.yaml</a>                                                                                                                                      | -                                                                                                                                                              |
| Swe Pivot                                     | agent                 | SWE pivot verifier for PivotRL on coding agent trajectories                                                                                                                                                                                                                                                                                                                                                                     | Improve coding agent fix-design decisions                                                                                             | ✓     | ✓          | Apache 2.0                                                | <a href='resources_servers/swe_pivot/configs/swe_pivot.yaml'>swe_pivot.yaml</a>                                                                                                                                                     | -                                                                                                                                                              |
| Swe Rebench                                   |                       | -                                                                                                                                                                                                                                                                                                                                                                                                                               | -                                                                                                                                     | -     | -          | -                                                         | <a href='resources_servers/swe_rebench/configs/swe_rebench_example.yaml'>swe_rebench_example.yaml</a>                                                                                                                               | -                                                                                                                                                              |
| Swe Rebench                                   |                       | -                                                                                                                                                                                                                                                                                                                                                                                                                               | -                                                                                                                                     | ✓     | -          | Creative Commons Attribution 4.0 International            | <a href='resources_servers/swe_rebench/configs/swe_rebench_opencode.yaml'>swe_rebench_opencode.yaml</a>                                                                                                                             | -                                                                                                                                                              |
| Swemer Oml                                    |                       | -                                                                                                                                                                                                                                                                                                                                                                                                                               | -                                                                                                                                     | -     | -          | -                                                         | <a href='resources_servers/swemer_oml/configs/swemer_oml_example.yaml'>swemer_oml_example.yaml</a>                                                                                                                                  | -                                                                                                                                                              |
| Swemer Oml                                    |                       | -                                                                                                                                                                                                                                                                                                                                                                                                                               | -                                                                                                                                     | ✓     | -          | NVIDIA Internal Use Only, Do Not Distribute               | <a href='resources_servers/swemer_oml/configs/swemer_oml_opencode.yaml'>swemer_oml_opencode.yaml</a>                                                                                                                                | -                                                                                                                                                              |
| Swemer Ultra                                  |                       | -                                                                                                                                                                                                                                                                                                                                                                                                                               | -                                                                                                                                     | -     | -          | -                                                         | <a href='resources_servers/swemer_ultra/configs/swemer_ultra_example.yaml'>swemer_ultra_example.yaml</a>                                                                                                                            | -                                                                                                                                                              |
| Swemer Ultra                                  |                       | -                                                                                                                                                                                                                                                                                                                                                                                                                               | -                                                                                                                                     | ✓     | -          | NVIDIA Internal Use Only, Do Not Distribute               | <a href='resources_servers/swemer_ultra/configs/swemer_ultra_opencode.yaml'>swemer_ultra_opencode.yaml</a>                                                                                                                          | -                                                                                                                                                              |
| Swemer V1                                     |                       | -                                                                                                                                                                                                                                                                                                                                                                                                                               | -                                                                                                                                     | -     | -          | -                                                         | <a href='resources_servers/swemer_v1/configs/swemer_v1_example.yaml'>swemer_v1_example.yaml</a>                                                                                                                                     | -                                                                                                                                                              |
| Swemer V1                                     |                       | -                                                                                                                                                                                                                                                                                                                                                                                                                               | -                                                                                                                                     | ✓     | -          | NVIDIA Internal Use Only, Do Not Distribute               | <a href='resources_servers/swemer_v1/configs/swemer_v1_opencode.yaml'>swemer_v1_opencode.yaml</a>                                                                                                                                   | -                                                                                                                                                              |
| Swemer V2                                     |                       | -                                                                                                                                                                                                                                                                                                                                                                                                                               | -                                                                                                                                     | -     | -          | -                                                         | <a href='resources_servers/swemer_v2/configs/swemer_v2_example.yaml'>swemer_v2_example.yaml</a>                                                                                                                                     | -                                                                                                                                                              |
| Swemer V2                                     |                       | -                                                                                                                                                                                                                                                                                                                                                                                                                               | -                                                                                                                                     | ✓     | -          | NVIDIA Internal Use Only, Do Not Distribute               | <a href='resources_servers/swemer_v2/configs/swemer_v2_opencode.yaml'>swemer_v2_opencode.yaml</a>                                                                                                                                   | -                                                                                                                                                              |
| Swerl Gen                                     | coding                | Running sandboxed evaluation for SWE-style tasks (either patch generation or reproduction test generation)                                                                                                                                                                                                                                                                                                                      | Improve SWE capabilities useful for benchmarks like SWE-bench                                                                         | ✓     | ✓          | Apache 2.0                                                | <a href='resources_servers/swerl_gen/configs/swerl_gen.yaml'>swerl_gen.yaml</a>                                                                                                                                                     | -                                                                                                                                                              |
| Swerl Llm Judge                               | coding                | SWE-style multiple-choice LLM-judge tasks scored via <solution>...</solution> choice.                                                                                                                                                                                                                                                                                                                                           | Improve SWE capabilities useful for benchmarks like SWE-bench                                                                         | ✓     | ✓          | MIT                                                       | <a href='resources_servers/swerl_llm_judge/configs/swerl_llm_judge.yaml'>swerl_llm_judge.yaml</a>                                                                                                                                   | -                                                                                                                                                              |
| Tales                                         | games                 | TALES text-adventure games (textworld, textworld_express, alfworld, scienceworld, jericho) in Gymnasium API style.                                                                                                                                                                                                                                                                                                              | Multi-turn reasoning and progress through open-ended, situated text environments.                                                     | -     | -          | -                                                         | <a href='resources_servers/tales/configs/tales.yaml'>tales.yaml</a>                                                                                                                                                                 | -                                                                                                                                                              |
| Tau2                                          | agent                 | Tau2 benchmark integration                                                                                                                                                                                                                                                                                                                                                                                                      | Evaluate multi-turn agentic capability with user simulation.                                                                          | -     | -          | -                                                         | <a href='responses_api_agents/tau2/configs/tau2.yaml'>tau2.yaml</a>                                                                                                                                                                 | -                                                                                                                                                              |
| Tau2                                          | agent                 | Tau2 benchmark integration with a 10-agent-step limit                                                                                                                                                                                                                                                                                                                                                                           | Evaluate multi-turn agentic capability with user simulation and a turn limit.                                                         | -     | -          | -                                                         | <a href='responses_api_agents/tau2/configs/tau2_agent_turn_limit.yaml'>tau2_agent_turn_limit.yaml</a>                                                                                                                               | -                                                                                                                                                              |
| Tavily Search                                 | agent                 | Model uses search tools to satisfy a user query.                                                                                                                                                                                                                                                                                                                                                                                | Measure agentic search capability                                                                                                     | ✓     | ✓          | Apache 2.0                                                | <a href='resources_servers/tavily_search/configs/tavily_search_judge_vllm_model.yaml'>tavily_search_judge_vllm_model.yaml</a>                                                                                                       | -                                                                                                                                                              |
| Terminal Bench 4                              | coding                | Official pinned TB4 setup, state, separate verification, and cleanup.                                                                                                                                                                                                                                                                                                                                                           | -                                                                                                                                     | -     | -          | -                                                         | <a href='resources_servers/terminal_bench_4/configs/terminal_bench_4.yaml'>terminal_bench_4.yaml</a>                                                                                                                                | -                                                                                                                                                              |
| Terminal Multi Harness                        | agent                 | Agent006 harness structured-action verifier for next-step pivot RL.                                                                                                                                                                                                                                                                                                                                                             | -                                                                                                                                     | -     | -          | -                                                         | <a href='resources_servers/terminal_multi_harness/configs/terminal_multi_harness_agent006.yaml'>terminal_multi_harness_agent006.yaml</a>                                                                                            | -                                                                                                                                                              |
| Terminal Multi Harness                        | agent                 | Codex harness structured-action verifier for next-step pivot RL.                                                                                                                                                                                                                                                                                                                                                                | -                                                                                                                                     | -     | -          | -                                                         | <a href='resources_servers/terminal_multi_harness/configs/terminal_multi_harness_codex.yaml'>terminal_multi_harness_codex.yaml</a>                                                                                                  | -                                                                                                                                                              |
| Terminal Multi Harness                        | agent                 | OpenCode harness structured-action verifier for next-step pivot RL.                                                                                                                                                                                                                                                                                                                                                             | -                                                                                                                                     | -     | -          | -                                                         | <a href='resources_servers/terminal_multi_harness/configs/terminal_multi_harness_opencode.yaml'>terminal_multi_harness_opencode.yaml</a>                                                                                            | -                                                                                                                                                              |
| Terminal Multi Harness                        | agent                 | Stirrup harness structured-action verifier for next-step pivot RL.                                                                                                                                                                                                                                                                                                                                                              | -                                                                                                                                     | -     | -          | -                                                         | <a href='resources_servers/terminal_multi_harness/configs/terminal_multi_harness_stirrup.yaml'>terminal_multi_harness_stirrup.yaml</a>                                                                                              | -                                                                                                                                                              |
| Terminus Judge                                | agent                 | single-step terminal based task (rubrics v4 judge prompt)                                                                                                                                                                                                                                                                                                                                                                       | Improve on terminal-style tasks                                                                                                       | ✓     | ✓          | Apache 2.0                                                | <a href='resources_servers/terminus_judge/configs/terminus_judge.yaml'>terminus_judge.yaml</a>                                                                                                                                      | -                                                                                                                                                              |
| Terminus Judge                                | agent                 | single-step terminal based task (simple judge prompt)                                                                                                                                                                                                                                                                                                                                                                           | Improve on terminal-style tasks                                                                                                       | ✓     | ✓          | Apache 2.0                                                | <a href='resources_servers/terminus_judge/configs/terminus_judge_simple.yaml'>terminus_judge_simple.yaml</a>                                                                                                                        | -                                                                                                                                                              |
| Terminus Judge                                | agent                 | single-step terminal based task (string similarity only)                                                                                                                                                                                                                                                                                                                                                                        | Improve on terminal-style tasks                                                                                                       | ✓     | ✓          | Apache 2.0                                                | <a href='resources_servers/terminus_judge/configs/terminus_judge_string_only.yaml'>terminus_judge_string_only.yaml</a>                                                                                                              | -                                                                                                                                                              |
| Text To Sql                                   | coding                | Text-to-SQL generation with LLM-as-a-judge equivalence checking                                                                                                                                                                                                                                                                                                                                                                 | Improve text-to-SQL capabilities across multiple dialects                                                                             | -     | -          | -                                                         | <a href='resources_servers/text_to_sql/configs/text_to_sql.yaml'>text_to_sql.yaml</a>                                                                                                                                               | -                                                                                                                                                              |
| Toolsandbox                                   | agent                 | ToolSandbox multi-turn tool-use benchmark; reward is the milestone similarity in [0, 1] (0 if a minefield is hit).                                                                                                                                                                                                                                                                                                              | Improve stateful, multi-turn tool-calling and user-interaction capability.                                                            | -     | ✓          | -                                                         | <a href='resources_servers/toolsandbox/configs/toolsandbox.yaml'>toolsandbox.yaml</a>                                                                                                                                               | -                                                                                                                                                              |
| Ugphysics Judge                               | knowledge             | Undergraduate physics QA verified by a TRUE/FALSE LLM judge with math-verify symbolic fallback                                                                                                                                                                                                                                                                                                                                  | Score undergraduate-physics benchmarks (e.g. UGPhysics) where the judge is a TRUE/FALSE equivalence grader using a reference solution | -     | -          | -                                                         | <a href='resources_servers/ugphysics_judge/configs/ugphysics_judge.yaml'>ugphysics_judge.yaml</a>                                                                                                                                   | -                                                                                                                                                              |
| Vcqa Agent                                    | coding                | Verified Code QA - investigate a per-task repo snapshot or git bundle, then answer against a must-have rubric graded by an LLM judge.                                                                                                                                                                                                                                                                                           | Code investigation across fileset and git-history tasks.                                                                              | ✓     | ✓          | Apache 2.0                                                | <a href='responses_api_agents/vcqa_agent/configs/vcqa_agent.yaml'>vcqa_agent.yaml</a>                                                                                                                                               | <a href='https://huggingface.co/datasets/appliedcompute/vcqa-v1'>vcqa-v1</a>                                                                                   |
| Verifiers Agent                               | math                  | Prime intellect verifiers and environments hub integration, ace-reason math environment example.                                                                                                                                                                                                                                                                                                                                | Improve math reasoning capabilities.                                                                                                  | ✓     | -          | -                                                         | <a href='responses_api_agents/verifiers_agent/configs/verifiers_agent.yaml'>verifiers_agent.yaml</a>                                                                                                                                | -                                                                                                                                                              |
| Verifif                                       | instruction_following | VerifIF instruction following validators with rule-based and LLM judge support                                                                                                                                                                                                                                                                                                                                                  | Improve instruction following capabilities with comprehensive validation                                                              | -     | -          | -                                                         | <a href='resources_servers/verifif/configs/verifif.yaml'>verifif.yaml</a>                                                                                                                                                           | -                                                                                                                                                              |
| Vibench                                       | coding                | PRD-to-web-app benchmark; apps are graded by seeding and driving them in a browser.                                                                                                                                                                                                                                                                                                                                             | Eval whether a model can ship a working web app from a spec, judged through the running UI rather than the diff.                      | -     | -          | -                                                         | <a href='resources_servers/vibench/configs/vibench.yaml'>vibench.yaml</a>                                                                                                                                                           | -                                                                                                                                                              |
| Vlm Eval Kit                                  | other                 | -                                                                                                                                                                                                                                                                                                                                                                                                                               | Measure VLM capabilities                                                                                                              | -     | ✓          | -                                                         | <a href='resources_servers/vlm_eval_kit/configs/MMBench_DEV_EN_V11.yaml'>MMBench_DEV_EN_V11.yaml</a>                                                                                                                                | -                                                                                                                                                              |
| Vlm Eval Kit                                  | other                 | -                                                                                                                                                                                                                                                                                                                                                                                                                               | Measure VLM capabilities                                                                                                              | -     | ✓          | -                                                         | <a href='resources_servers/vlm_eval_kit/configs/OCRBench.yaml'>OCRBench.yaml</a>                                                                                                                                                    | -                                                                                                                                                              |
| Vlm Eval Kit                                  | other                 | Run all supported VLMEvalKit benchmarks.                                                                                                                                                                                                                                                                                                                                                                                        | Measure VLM capabilities                                                                                                              | -     | ✓          | -                                                         | <a href='resources_servers/vlm_eval_kit/configs/vlm_eval_kit.yaml'>vlm_eval_kit.yaml</a>                                                                                                                                            | -                                                                                                                                                              |
| Voicebench                                    | e2e                   | Synthetic text smoke examples for the VoiceBench legacy MCQ scorer                                                                                                                                                                                                                                                                                                                                                              | -                                                                                                                                     | -     | -          | -                                                         | <a href='resources_servers/voicebench/configs/voicebench_example.yaml'>voicebench_example.yaml</a>                                                                                                                                  | -                                                                                                                                                              |
| Widesearch                                    | knowledge             | Grade structured WideSearch Markdown tables                                                                                                                                                                                                                                                                                                                                                                                     | Evaluate broad web research coverage and accuracy                                                                                     | -     | -          | -                                                         | <a href='resources_servers/widesearch/configs/widesearch.yaml'>widesearch.yaml</a>                                                                                                                                                  | -                                                                                                                                                              |
| Wmt Translation                               | other                 | Machine-translation verifier computing corpus-level spBLEU and ChrF per language pair plus optional xCOMET-XXL neural QE via a Ray GPU actor.                                                                                                                                                                                                                                                                                   | Improves multilingual translation quality across spBLEU, ChrF, and COMET-family metrics.                                              | -     | -          | -                                                         | <a href='resources_servers/wmt_translation/configs/wmt_translation.yaml'>wmt_translation.yaml</a>                                                                                                                                   | -                                                                                                                                                              |
| Wordle                                        | games                 | Wordle word-guessing game environment for training LLMs                                                                                                                                                                                                                                                                                                                                                                         | Improve strategic reasoning and letter pattern recognition                                                                            | ✓     | ✓          | Apache 2.0                                                | <a href='resources_servers/wordle/configs/wordle.yaml'>wordle.yaml</a>                                                                                                                                                              | -                                                                                                                                                              |
| Workplace Assistant                           | agent                 | Workplace assistant multi-step tool-using environment                                                                                                                                                                                                                                                                                                                                                                           | Improve multi-step tool use capability                                                                                                | ✓     | ✓          | Apache 2.0                                                | <a href='resources_servers/workplace_assistant/configs/workplace_assistant.yaml'>workplace_assistant.yaml</a>                                                                                                                       | <a href='https://huggingface.co/datasets/nvidia/Nemotron-RL-agent-workplace_assistant'>Nemotron-RL-agent-workplace_assistant</a>                               |
| Xlam Fc                                       | agent                 | Salesforce xlam-function-calling-60k tool calling tasks                                                                                                                                                                                                                                                                                                                                                                         | Improve tool-calling capabilities                                                                                                     | ✓     | ✓          | Apache 2.0                                                | <a href='resources_servers/xlam_fc/configs/xlam_fc.yaml'>xlam_fc.yaml</a>                                                                                                                                                           | -                                                                                                                                                              |
| Xstest                                        | safety                | XSTest safety benchmark - exaggerated safety (over-refusal) evaluation                                                                                                                                                                                                                                                                                                                                                          | Evaluate model safety calibration between helpfulness and harmlessness                                                                | -     | -          | -                                                         | <a href='resources_servers/xstest/configs/xstest.yaml'>xstest.yaml</a>                                                                                                                                                              | -                                                                                                                                                              |

## 📖 Documentation & Resources

- **[Documentation](https://docs.nvidia.com/nemo/gym/main)** - Technical reference docs
- **[Environment Tutorials](https://docs.nvidia.com/nemo/gym/main/environment-tutorials)** - Build custom environments
- **[Training Tutorials](https://docs.nvidia.com/nemo/gym/tutorials/training-tutorials)** - Train with NeMo Gym environments
- **[API Reference](https://docs.nvidia.com/nemo/gym/main/api/reference/api-reference)** - Complete class and function reference
- **[Observability](https://docs.nvidia.com/nemo/gym/main/observability)** - OpenTelemetry traces, metrics, and distributed tracing

## 🤝 Community & Support

We'd love your contributions! Here's how to get involved:

- **[Report Issues](https://github.com/NVIDIA-NeMo/Gym/issues)** - Bug reports and feature requests
- **[Contributing Guide](https://docs.nvidia.com/nemo/gym/main/contribute)** - How to contribute code, docs, new environments, or training framework integrations

## 📚 Citations

If you use NeMo Gym in your research, please cite it using the following BibTeX entry:

```bibtex
@misc{nemo-gym,
  title = {NeMo Gym: An Open Source Library for Scaling Reinforcement Learning Environments for LLM},
  howpublished = {\url{https://github.com/NVIDIA-NeMo/Gym}},
  author={NVIDIA},
  year = {2025},
  note = {GitHub repository},
}
```

## ⚠️ Notice and Disclaimer

This software automatically retrieves, accesses or interacts with external materials. Those retrieved materials are not distributed with this software and are governed solely by separate terms, conditions and licenses. You are solely responsible for finding, reviewing and complying with all applicable terms, conditions, and licenses, and for verifying the security, integrity and suitability of any retrieved materials for your specific use case. This software is provided "AS IS", without warranty of any kind. The author makes no representations or warranties regarding any retrieved materials, and assumes no liability for any losses, damages, liabilities or legal consequences from your use or inability to use this software or any retrieved materials. Use this software and the retrieved materials at your own risk.

Repository info

Default branch: main
Latest version: v0.7.0
Created: 26/08/2025
Last activity: 05/11/2026
License: Apache-2.0
Open issues: 1.4k
Watchers: 8

Topics

agents benchmarks environments evaluation gym llm reinforcement-learning reinforcement-learning-environments rl-environment rl-training

Contributors

ananthsub

211 contributions

bxyu-nvidia

177 contributions

cmunley1

128 contributions

cwing-nvidia

83 contributions

kajalj22

83 contributions