NeMo Gym

August 3, 2026 · View on GitHub

Requirements • Quick Start • Environment Tutorials • Available Environments • Documentation & Resources • Community & Support • 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
Battle-tested in production Nemotron training

NeMo Gym Product Overview

🌎 Ecosystem

NeMo Gym is a component of NVIDIA NeMo, 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 page for more details.

Environment Libraries: Seamlessly combine environments and benchmarks from other libraries alongside NeMo Gym environments. Examples: Aviary • Harbor • OpenEnv • Reasoning Gym • Verifiers

Training Framework Libraries: Use environments for SFT and RL training. NeMo RL • Unsloth • VeRL

Agent Harnesses: Agent harnesses for evaluation and training available out of the box. Examples: OpenHands • Mini SWE Agent • LangGraph

Important

NeMo Gym is currently in early development. You should expect evolving APIs, incomplete documentation, and occasional bugs. We welcome contributions and feedback - for any changes, please open an issue first to kick off discussion!

📣 News

[07/01/2026] Release v0.4.0:
- Unified gym CLI: discover agents and benchmarks with gym list, catch config errors before a run with gym env validate
- BLADE diagnostics: an analysis skill that reads your eval results and reports which tasks failed, why, and the highest-impact fix
- Agent skill evaluation: run the same tasks with different skill sets to measure each skill's impact
- Pluggable sandboxes: run tool-using agents in isolated environments via the sandbox provider of your choice
- More agent harnesses: OpenCode, OpenClaw, and Pi available out of the box
- Hosted inference providers: connect to Fireworks, Together.ai, OpenRouter, and more
- New benchmarks: across science, long-context, and interactive tasks

Previous News

[06/04/2026] Release v0.3.0!: 70+ new environments, Nemotron 3 Ultra training datasets, VeRL integration, and out-of-the-box harnesses including Claude Code and Hermes.

📋 Requirements

NeMo Gym is designed to run on standard development machines:

Hardware Requirements	Software Requirements
GPU: Not required for NeMo Gym library operation • GPU may be needed for specific resources servers or model inference (see individual server documentation)	Operating System: • Linux (Ubuntu 20.04+, or equivalent) • macOS (11.0+ for x86_64, 12.0+ for Apple Silicon) • Windows (via WSL2)
CPU: Any modern x86_64 or ARM64 processor (e.g., Intel, AMD, Apple Silicon)	Python: 3.12 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 3.12+ on x86_64 or ARM64 (Linux, macOS, Windows via WSL2). No GPU required. See the Getting Started docs for a more comprehensive walkthrough.

Install NeMo Gym:

Requires uv and Python 3.12+.

git clone git@github.com:NVIDIA-NeMo/Gym.git
cd Gym
uv venv --python 3.12 && source .venv/bin/activate
uv sync

Configure your model:

This quickstart uses OpenAI. NeMo Gym supports local and hosted inference — see Configure Model for vLLM, Fireworks, OpenRouter, and others.

Create env.yaml in the project root:

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 with the mcqa (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:

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

You should see three server instances starting:

[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:

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:

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 command.

Next Steps

Browse Environments — Browse available environments for evaluation and training.
Agents — Explore available agent harnesses and learn how to integrate your own.
Training — Improve your agent or model with RL or fine-tuning.
Build Custom Environments — 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	Basic single-step tool calling
Multi Step	Multi-step tool calling
Session State	Session state management (in-memory)
Multi Reward	Multiple reward components for evaluation and multi-objective RL (e.g. GDPO)

See all 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	-	-	-	-	-	aalcr.yaml	-
Abstention	rlhf	Train models to abstain when unsure using three-tier reward on HotPotQA with LLM judge	Improve calibration by rewarding abstention over incorrect answers	✓	✓	Creative Commons Attribution-ShareAlike 4.0 International	abstention.yaml	-
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.	-	-	-	anyswe_claude_code.yaml	-
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.	-	-	-	anyswe_hermes.yaml	-
Anyswe Agent	coding	SWE-bench run by OpenClaw natively inside the task container.	Eval software engineering capabilities on SWE-bench with any Gym agent.	-	-	-	anyswe_openclaw.yaml	-
Anyswe Agent	coding	SWE-bench run by OpenCode inside the task container.	Eval software engineering capabilities on SWE-bench with any Gym agent.	-	-	-	anyswe_opencode.yaml	-
Anyswe Agent	coding	SWE-bench run by Pi inside the task container.	Eval software engineering capabilities on SWE-bench with any Gym agent.	-	-	-	anyswe_pi.yaml	-
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.	-	-	-	anyterminal_claude_code.yaml	-
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.	-	-	-	anyterminal_hermes.yaml	-
Arc Agi	knowledge	Solve puzzles designed to test intelligence. See https://arcprize.org/arc-agi.	Improve puzzle-solving capabilities.	-	✓	-	arc_agi.yaml	-
Arena Judge		-	-	-	-	-	arena_judge.yaml	-
Asr With Pc	other	ASR with WER scoring (standard, case-sensitive, punctuation+capitalization)	Improve transcription quality with structural detail	-	-	-	asr_with_pc.yaml	-
Aviary	agent	Multi-hop question answering on the HotPotQA dataset with Wikipedia search	Improve knowledge and agentic capability	✓	✓	Apache 2.0	hotpotqa_aviary.yaml	-
Aviary	math	GSM8k benchmark with calculator tool	Test math and agentic capability	✓	✓	Apache 2.0	gsm8k_aviary.yaml	-
Bigcodebench	coding	Verifies model-generated Python solutions against the BigCodeBench unittest suite.	Improve practical, library-rich Python coding capabilities.	-	-	-	bigcodebench.yaml	-
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.	-	-	-	bird_sql.yaml	-
Blackjack	games	Blackjack. Model hits or stands. Reward +1 win, 0 draw, -1 loss/bust.	Example gymnasium-style multi-step environment	-	-	-	blackjack.yaml	-
Browsecomp Advanced Harness	agent	Model uses search tools to satisfy a user query.	Measure agentic search capability	-	-	-	browsecomp_advanced_harness.yaml	-
Bunsenbench Chemistry Mcq	knowledge	Public BunsenBench chemistry multiple-choice benchmark verifier	Measure chemistry MCQ reasoning with source and taxonomy breakdowns	-	-	-	bunsenbench_chemistry_mcq.yaml	-
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	calendar.yaml	Nemotron-RL-agent-calendar_scheduling
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	calendar_v2.yaml	Nemotron-RL-Instruction-Following-Calendar-v2
Circle Click	other	Click on circles in images	Improve visual grounding and spatial reasoning	-	-	-	circle_click.yaml	-
Circle Count	other	Count circles of a given color in images	Improve visual counting and color recognition	-	-	-	circle_count.yaml	-
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)	-	-	-	code_fim.yaml	-
Code Gen	coding	Model must submit the right code to solve a problem	Improve competitive coding capabilities	✓	✓	Apache 2.0	code_gen.yaml	nemotron-RL-coding-competitive_coding
Competitive Coding Challenges	coding	Execution of competitive programming competition questions	Improve competitive coding capabilities on contest-style problems	-	-	-	competitive_coding_challenges.yaml	-
Critpt	other	Research-level physics problems scored by the Artificial Analysis API	Evaluate model performance on research-level physics reasoning	-	-	-	critpt.yaml	-
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	nl2bash-equivalency.yaml	-
Equivalence Llm Judge	knowledge	Short answer questions with LLM-as-a-judge	Improve knowledge-related benchmarks like GPQA / HLE	-	-	-	equivalence_llm_judge.yaml	-
Equivalence Rule	knowledge	Question - Answering with rule-based reward	Improve retrieval and counting capabilities	-	-	-	lc.yaml	-
Ether0	knowledge	ether0 chemistry benchmark verifiers	Evaluate chemistry knowledge and reasoning with ether0 benchmark	-	✓	-	ether0.yaml	-
Evalplus	coding	Function-completion code judged by EvalPlus base + plus tests (HumanEval+, MBPP+)	Improve Python function-completion capabilities	-	-	-	evalplus.yaml	-
Finance Sec Search	agent	SEC EDGAR filing search for financial analysis questions	Enable LLMs to search and analyze SEC filings	-	-	-	finance_sec_search.yaml	-
Format Verification	instruction_following	Verify citation/reference markers in model responses via string matching	Improve instruction following for citation format adherence	✓	-	Apache 2.0	citation_format.yaml	-
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	freeform_formatting.yaml	-
Frontierscience Judge	other	FrontierScience answer grading via single-pass LLM judge	Evaluate FrontierScience Olympiad short answers or Research rubric-scored answers	-	-	-	frontierscience_judge.yaml	-
Genrm Compare	rlhf	GenRM pairwise comparison for RLHF training	Compare multiple candidate responses using GenRM model	-	-	-	genrm_compare.yaml	-
Google Search	agent	Multi-choice question answering problems with search tools integrated	Improve knowledge-related benchmarks with search tools	✓	-	Apache 2.0	google_search.yaml	Nemotron-RL-knowledge-web_search-mcqa
Gpqa Diamond	knowledge	GPQA Diamond multiple-choice question answering problems	Evaluate graduate-level scientific reasoning via MCQ verification	✓	-	MIT	gpqa_diamond.yaml	-
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	-	-	-	graphwalks.yaml	-
Grl Sokoban	games	Single-box Sokoban in Gymnasium API style.	Model emits one move per turn until the puzzle is solved.	-	-	-	grl_sokoban.yaml	-
Grl Tetris	games	Tetris in Gymnasium API style. Model emits one or more moves per turn.	Multi-step Tetris environment	-	-	-	grl_tetris.yaml	-
Gymnasium	other	Base class for Gymnasium-style servers. Not a standalone server.	Reusable base class for step/reset style environments	-	-	-	gymnasium.yaml	-
Harbor Agent	agent	Fast local smoketest task (trivial 1-turn task, no LLM judge) for iterating on the Gym<->Harbor bridge.	-	✓	-	-	harbor_agent_smoketest_docker.yaml	-
Harbor Agent	agent	Harbor integration for agent harnesses and environments.	Improve models in popular agentic environments supported by Harbor such as Terminus2.	✓	-	-	harbor_agent.yaml	-
Harbor Agent	agent	Harbor integration for agent harnesses and environments.	Improve models in popular agentic environments supported by Harbor such as Terminus2.	✓	-	-	harbor_agent_daytona.yaml	-
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.	-	-	-	hotpotqa_qa.yaml	-
Ifbench	instruction_following	IFBench instruction following evaluation using AllenAI's IFBench library (57 instruction types)	Improve IFBench instruction following	-	-	-	ifbench.yaml	-
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.	-	✓	-	iheval.yaml	-
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.	-	-	-	imo_gradingbench.yaml	-
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	-	-	-	imo_proofbench_judge.yaml	-
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	indirect_prompt_injection.yaml	-
Instruction Following	instruction_following	Instruction following datasets targeting IFEval and IFBench style instruction following capabilities	Improve IFEval and IFBench	✓	-	Apache 2.0	instruction_following.yaml	Nemotron-RL-instruction_following
Inverse If	knowledge	Inverse IF instruction-following benchmark with per-task LLM judge	-	✓	-	TBD	inverse_if.yaml	-
Jailbreak Detection	safety	Jailbreak detection with Nemotron judge + combined reward	Improve Jailbreak Robustness and Safety/Security Behavior Guide Enforcement	-	-	-	jailbreak_detection_nemotron_combined_reward_tp8.yaml	-
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	-	✓	-	labbench2_vlm.yaml	-
Lc Niah	knowledge	Answer-correctness reward gated by low reasoning/input overlap	Reward correct answers while discouraging copying the prompt into reasoning	-	-	-	lc_niah.yaml	-
Legal Agent Bench	agent	Harbor-native integration of Legal Agent Benchmark (LAB)	Improve legal-agent document review, drafting, and analysis capability	-	✓	-	legal_agent_bench.yaml	-
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".	✓	-	Creative Commons Attribution 4.0 International	litmus_agent.yaml	Nemotron-RL-litmus-bench-v0.1
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".	✓	-	Creative Commons Attribution 4.0 International	litmus_agent_apptainer.yaml	Nemotron-RL-litmus-bench-v0.1
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.	-	-	-	longmt_pg19.yaml	-
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.	-	-	-	longmt_wmt24pp.yaml	-
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.	-	-	-	longmt_eval.yaml	-
Math Advanced Calculations	agent	An instruction following math environment with counter-intuitive calculators	Improve instruction following capabilities in specific math environments	✓	-	Apache 2.0	math_advanced_calculations.yaml	Nemotron-RL-math-advanced_calculations
Math Formal Lean	math	Lean4 formal proof verification environment	Improve formal theorem proving capabilities	✓	-	Apache 2.0	nemotron_clean_easy.yaml	-
Math Formal Lean	math	Lean4 formal proof verification environment	Improve formal theorem proving capabilities	✓	-	Apache 2.0	nemotron_first_try_hard.yaml	-
Math Formal Lean	math	Lean4 formal proof verification environment	Improve formal theorem proving capabilities	✓	-	Apache 2.0	nemotron_medium_500.yaml	-
Math Formal Lean	math	Lean4 formal proof verification environment	Improve formal theorem proving capabilities	✓	-	Apache 2.0	nemotron_very_easy.yaml	-
Math Formal Lean	math	Lean4 formal proof verification environment	Improve formal theorem proving capabilities	✓	-	MIT	math_formal_lean.yaml	-
Math Formal Lean	math	Lean4 formal proof verification environment with multi-turn self-correction	Improve formal theorem proving capabilities	✓	-	MIT	math_formal_lean_multi_turn.yaml	-
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.	-	-	-	math_proof_judgement.yaml	-
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	-	-	-	math_with_autograder.yaml	-
Math With Code	math	Model solves competitive math problems using simple calculator tools	Improve math and simple tool use capabilities	✓	-	Apache 2.0	math_with_code.yaml	-
Math With Judge	math	DAPO17k math dataset with math-verify	Improve math capabilities including AIME 24 / 25	✓	✓	Apache 2.0	dapo17k.yaml	-
Math With Judge	math	Hermes Agent with terminal, file, code_execution, skills, todo toolsets on OpenMathReasoning math dataset with math-verify and LLM-as-a-judge	Improve model math capabilities in hermes agent harness such as AIME25	✓	-	Creative Commons Attribution 4.0 International	math_with_judge_hermes_agent.yaml	Nemotron-RL-math-OpenMathReasoning
Math With Judge	math	KiloCode agent harness on OpenMathReasoning math dataset with math-verify	Improve model math capabilities in the KiloCode agent harness	-	-	-	math_with_judge_kilocode_agent.yaml	-
Math With Judge	math	MathStackOverflow math dataset with math-verify	Improve math capabilities including AIME 24 / 25	✓	✓	Creative Commons Attribution-ShareAlike 4.0 International	math_stack_overflow.yaml	Nemotron-RL-math-stack_overflow
Math With Judge	math	OpenClaw agent harness on OpenMathReasoning math dataset with math-verify	Improve model math capabilities in the OpenClaw agent harness	-	-	-	math_with_judge_openclaw_agent.yaml	-
Math With Judge	math	OpenCode agent harness on OpenMathReasoning math dataset with math-verify	Improve model math capabilities in the OpenCode agent harness	-	-	-	math_with_judge_opencode_agent.yaml	-
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	math_with_judge.yaml	Nemotron-RL-math-OpenMathReasoning
Math With Judge	math	pi agent harness on OpenMathReasoning math dataset with math-verify	Improve model math capabilities in the pi agent harness	-	-	-	math_with_judge_pi_agent.yaml	-
Mcqa	knowledge	Multi-choice question answering problems	Improve benchmarks like MMLU / GPQA / HLE	✓	✓	Apache 2.0	mcqa.yaml	Nemotron-RL-knowledge-mcqa
Mini Swe Agent	coding	Software engineering tasks driven by mini-swe agent harness.	Improve agentic software engineering capabilities.	✓	✓	MIT	mini_swe_agent.yaml	SWE-Gym
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	-	-	-	mrcr.yaml	-
Multichallenge	knowledge	Targets inference memory, instruction retention, version editing, and self-coherence.	Improve complex multi-turn conversational capability	✓	-	Creative Commons Attribution 4.0 International	multichallenge_nrl.yaml	Nemotron-RL-Instruction-Following-MultiTurnChat-v1
Newton Bench	math	Scientific law discovery tasks through agentic experimentation across 12 physics domains	Improve science, reasoning, and tool use capabilities	✓	-	Apache 2.0	newton_bench.yaml	-
Ns Tools	agent	NeMo Skills tool execution with math verification	-	-	-	-	ns_tools.yaml	-
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	inductive.yaml	-
Nvarc	knowledge	ARC-AGI transductive mode: model outputs grid directly	Improve ARC-AGI puzzle-solving by directly predicting transformed grids	✓	✓	Apache 2.0	transductive.yaml	-
Omniscience	knowledge	Omniscience factual knowledge QA with LLM judge verification	Evaluate factual recall and calibration via LLM-graded open-ended QA	-	-	-	omniscience.yaml	-
Openenv	agent	Echo environment via OpenEnv (MCP). Echoes messages back with length-based rewards.	-	-	-	-	openenv_echo.yaml	-
Openenv	coding	Python code execution environment via OpenEnv. Executes code and returns stdout/stderr.	-	-	-	-	openenv_coding.yaml	-
Openenv	games	Maze navigation environment via OpenEnv. Agent navigates an 8x8 grid to find the exit.	-	-	-	-	openenv_maze.yaml	-
Over Refusal Detection		-	-	✓	-	TBD	over_refusal_detection.yaml	-
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	-	-	-	physics_judge.yaml	-
Pinchbench	agent	PinchBench benchmark integration	Evaluate a model as the brain of an OpenClaw agent on real-world tasks.	-	-	-	pinchbench.yaml	-
Polymath	math	PolyMath multilingual math benchmark with weighted (difficulty) and per-language metrics	Improve multilingual math reasoning across 18 languages and 4 difficulty tiers	-	-	-	polymath.yaml	-
Proof Genselect	math	Pairwise proof selection with binary correctness reward	-	-	-	-	proof_genselect.yaml	-
Proof Judge	math	Theorem proving with verifier + meta-verifier judge (combined env)	-	-	-	-	proof_judge.yaml	-
Proof Verification	math	Proof verification scored against ground truth and meta-verifier agreement	-	-	-	-	proof_verification.yaml	-
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.	-	✓	-	ragtruth.yaml	-
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	reasoning_gym_claude_code_agent.yaml	Nemotron-RL-ReasoningGym-v1
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	-	-	-	reasoning_gym_claude_code_agent_model_server.yaml	-
Reasoning Gym	knowledge	Codex agent harness for reasoning gym tasks	Evaluate model capabilities in the Codex agent harness	-	-	-	reasoning_gym_codex_agent.yaml	-
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	-	-	-	reasoning_gym_codex_agent_model_server.yaml	-
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	orchestrator_agent.yaml	-
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	parallel_thinking_agent.yaml	-
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	reflection_agent.yaml	-
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	rewoo_agent.yaml	-
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	reasoning_gym.yaml	Nemotron-RL-ReasoningGym-v1
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.	-	✓	-	rolemrc.yaml	-
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.	-	✓	-	rolemrc_judge.yaml	-
Ruler	other	-	-	-	-	-	ruler.yaml	-
Scicode	coding	Multi-step scientific code generation; sub-step solutions executed against SciCode test cases	Improve multi-step scientific code generation	-	-	-	scicode.yaml	-
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	-	-	-	simpleqa.yaml	-
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	single_step_tool_use_with_argument_comparison.yaml	Nemotron-RL-Agentic-Conversational-Tool-Use-Pivot-v1
Single Step Tool Use With Argument Comparison	agent	Droid agent pivot dataset; behavior cloning per step from successful Droid rollouts.	-	-	-	-	droid_pivot_single_step_tool_use_with_argument_comparison.yaml	-
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	toolcall_schema_single_step_tool_use_with_argument_comparison.yaml	Nemotron-RL-Agentic-Function-Calling-Pivot-v1
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	swe_pivot_single_step_tool_use_with_argument_comparison.yaml	Nemotron-RL-Agentic-SWE-Pivot-v1
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	search_pivot_single_step_tool_use_with_argument_comparison.yaml	-
Speed Bench	other	Speculative-decoding throughput benchmark. Reads vLLM `/metrics` Prometheus counters before/after generation to compute acceptance length and acceptance rate.	Measure inference-time speculative-decoding effectiveness for serving research and regression tests.	-	-	-	speed_bench.yaml	-
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.	-	✓	-	spider2_lite.yaml	-
Structeval	instruction_following	StructEval non-renderable format verification (JSON, YAML, CSV, TOML, XML)	Improve structured output generation quality	✓	-	Apache 2.0	structeval_nonrenderable.yaml	-
Structured Outputs	instruction_following	Check if responses are following structured output requirements in prompts	Improve instruction following capabilities	✓	✓	Apache 2.0	structured_outputs_json.yaml	Nemotron-RL-instruction_following-structured_outputs
Structured Outputs	instruction_following	Check if responses are following structured output requirements in prompts	Improve instruction following capabilities	✓	✓	Apache 2.0	structured_outputs_json_yaml_xml_v1.yaml	-
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	structured_outputs_v3.yaml	-
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	structured_outputs_v4.yaml	-
Swe Agents		-	-	✓	✓	Apache 2.0	swebench_multi_tools.yaml	-
Swe Agents		-	-	✓	✓	Apache 2.0	swebench_openhands.yaml	-
Swe Agents		-	-	✓	✓	Apache 2.0	swebench_openhands_training.yaml	-
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	swebench_opencode_training.yaml	-
Swe Agents	coding	SWE-bench driven by the opencode agent framework.	Eval software engineering capabilities on SWE-bench using opencode.	✓	✓	Apache 2.0	swebench_opencode.yaml	-
Swe Pivot	agent	SWE pivot verifier for PivotRL on coding agent trajectories	Improve coding agent fix-design decisions	✓	✓	Apache 2.0	swe_pivot.yaml	-
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	swerl_gen.yaml	-
Swerl Llm Judge	coding	SWE-style multiple-choice LLM-judge tasks scored via ... choice.	Improve SWE capabilities useful for benchmarks like SWE-bench	✓	✓	MIT	swerl_llm_judge.yaml	-
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.	-	-	-	tales.yaml	-
Tau2	agent	Tau2 benchmark integration	Evaluate multi-turn agentic capability with user simulation.	-	-	-	tau2_agent.yaml	-
Tau2	agent	Tau2 benchmark integration with a 10-agent-step limit	Evaluate multi-turn agentic capability with user simulation and a turn limit.	-	-	-	tau2_agent_turn_limit.yaml	-
Tavily Search	agent	Model uses search tools to satisfy a user query.	Measure agentic search capability	✓	✓	Apache 2.0	tavily_search_judge_vllm_model.yaml	-
Terminal Multi Harness	agent	Agent006 harness structured-action verifier for next-step pivot RL.	-	-	-	-	terminal_multi_harness_agent006.yaml	-
Terminal Multi Harness	agent	Codex harness structured-action verifier for next-step pivot RL.	-	-	-	-	terminal_multi_harness_codex.yaml	-
Terminal Multi Harness	agent	OpenCode harness structured-action verifier for next-step pivot RL.	-	-	-	-	terminal_multi_harness_opencode.yaml	-
Terminal Multi Harness	agent	Stirrup harness structured-action verifier for next-step pivot RL.	-	-	-	-	terminal_multi_harness_stirrup.yaml	-
Terminus Judge	agent	single-step terminal based task (rubrics v4 judge prompt)	Improve on terminal-style tasks	✓	✓	Apache 2.0	terminus_judge.yaml	-
Terminus Judge	agent	single-step terminal based task (simple judge prompt)	Improve on terminal-style tasks	✓	✓	Apache 2.0	terminus_judge_simple.yaml	-
Terminus Judge	agent	single-step terminal based task (string similarity only)	Improve on terminal-style tasks	✓	✓	Apache 2.0	terminus_judge_string_only.yaml	-
Text To Sql	coding	Text-to-SQL generation with LLM-as-a-judge equivalence checking	Improve text-to-SQL capabilities across multiple dialects	-	-	-	text_to_sql.yaml	-
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.	-	✓	-	toolsandbox.yaml	-
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	-	-	-	ugphysics_judge.yaml	-
Verifiers Agent	math	Prime intellect verifiers and environments hub integration, ace-reason math environment example.	Improve math reasoning capabilities.	✓	-	-	acereason-math.yaml	-
Verifif	instruction_following	VerifIF instruction following validators with rule-based and LLM judge support	Improve instruction following capabilities with comprehensive validation	-	-	-	verifif.yaml	-
Vlm Eval Kit	other	-	Measure VLM capabilities	-	✓	-	MMBench_DEV_EN_V11.yaml	-
Vlm Eval Kit	other	-	Measure VLM capabilities	-	✓	-	OCRBench.yaml	-
Vlm Eval Kit	other	Run all supported VLMEvalKit benchmarks.	Measure VLM capabilities	-	✓	-	vlm_eval_kit.yaml	-
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.	-	-	-	wmt_translation.yaml	-
Workplace Assistant	agent	Workplace assistant multi-step tool-using environment	Improve multi-step tool use capability	✓	✓	Apache 2.0	workplace_assistant.yaml	Nemotron-RL-agent-workplace_assistant
Xlam Fc	agent	Salesforce xlam-function-calling-60k tool calling tasks	Improve tool-calling capabilities	✓	✓	Apache 2.0	xlam_fc.yaml	-
Xstest	safety	XSTest safety benchmark - exaggerated safety (over-refusal) evaluation	Evaluate model safety calibration between helpfulness and harmlessness	-	-	-	xstest.yaml	-

📖 Documentation & Resources

Documentation - Technical reference docs
Environment Tutorials - Build custom environments
Training Tutorials - Train with NeMo Gym environments
API Reference - Complete class and function reference

🤝 Community & Support

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

Report Issues - Bug reports and feature requests
Contributing Guide - 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:

@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},
}