NeMo Gym

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
• Optional OpenTelemetry tracing across the agent, model, and resources servers
• Battle-tested in production Nemotron training

🌎 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

📣 News

• [10/06/2026] Release 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

Previous News

• [09/03/2026] Release 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: 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: 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: 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: 3.13.14 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 docs for a more comprehensive walkthrough.

Install NeMo Gym:

Requires uv and Python 3.13.14+.

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 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.

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 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 — 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 Nemotron-RL-QA-Abstention-v1 with LLM judge	Improve calibration by rewarding abstention over incorrect answers	✓	-	Creative Commons Attribution 4.0 International	abstention.yaml	Nemotron-RL-QA-Abstention-v1
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	-	-	-	aegis_v4_safety.yaml	-
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.	-	✓	-	agentif.yaml	-
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.	-	-	-	anyswe_nemo_fabric.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	-
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.	-	-	-	anyswe_cline.yaml	-
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.	-	-	-	anyterminal_nemo_fabric.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 OpenClaw natively inside the task container.	Evaluate terminal-task capabilities on Terminal Bench with any Gym agent.	-	-	-	anyterminal_openclaw.yaml	-
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.	-	-	-	anyterminal_terminus_2.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	rlhf	LMArena proxy v2 chat evaluation benchmark	Measure general chat quality via win rate against baseline responses	-	✓	-	lmarena_v2.yaml	-
Arena	rlhf	LMArena proxy v3 chat evaluation benchmark	Measure general chat quality via win rate against baseline responses	-	✓	-	lmarena_v3.yaml	-
Arena	rlhf	VisionArena-Bench v0.1 multimodal preference evaluation	Measure image-grounded answer quality against saved baseline responses	-	-	-	vision_arena_v1.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	-
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	-	-	-	assaybench.yaml	-
Bbq	safety	BBQ comparative QA with Answer and Explanation Quality checks	Evidence-grounded and fairness-safe comparative reasoning	-	-	-	bbq.yaml	-
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).	-	-	-	beam.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
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	-	-	-	chemreason_bench.yaml	-
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	-
Citation If	instruction_following	Citation instruction-following reward checker	Train models to follow citation format instructions in search-grounded synthesis tasks	-	-	-	citation_if.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	-
Conversational Tool Use Simulation	agent	Conversational tool-use simulation environment.	-	-	-	-	conversational_tool_use_simulation.yaml	-
Critpt	other	Research-level physics problems scored by the Artificial Analysis API	Evaluate model performance on research-level physics reasoning	-	-	-	critpt.yaml	-
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	-	-	-	critpt_custom_grader.yaml	-
Deepsearchqa	knowledge	Grade DeepSearchQA single-answer and set-answer responses	Evaluate multi-step web research answers	-	-	-	deepsearchqa.yaml	-
Denovo Swe		-	-	-	-	-	denovo_swe_example.yaml	-
Denovo Swe		-	-	✓	-	Creative Commons Attribution 4.0 International	denovo_swe_opencode.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	-
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	-	-	-	false_statement_judge.yaml	-
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	-	-	-	finance_agent_v2.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	-
Frontiermath	math	Exact boxed-answer verification for the FrontierMath public sample	Evaluate advanced mathematical reasoning across languages	-	-	-	frontiermath.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	-
Fukuyamabench	knowledge	FukuyamaBench organic reaction-mechanism pathway verifier	Evaluate step-by-step organic reaction mechanism prediction with FukuyamaBench	-	✓	-	fukuyamabench.yaml	-
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	-	-	-	gdp_pdf.yaml	-
Generative Reward Model	rlhf	Train GenRM to score and rank response pairs per-rubric and overall	-	✓	-	Apache 2.0	genrm_train.yaml	-
Genrm Compare	rlhf	GenRM pairwise comparison for RLHF training	Compare multiple candidate responses using GenRM model	-	-	-	genrm_compare.yaml	-
Genrm Eval		-	-	-	-	-	genrm_eval.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	-
Gui Coordinate	other	GUI coordinate grounding verifier for visual pointing tasks	Verify GUI coordinate predictions using smooth quadratic reward based on Euclidean distance	-	-	-	gui_coordinate.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_opensandbox.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	-
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	image_tools_pivot.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	-
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	indian_banking.yaml	nemo-gym-indian-banking
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
Interactive Browser	agent	Interactive browser environment — navigate/click/type/observe a live page; pluggable local (Playwright) or remote (CDP) browser backend.	-	-	-	-	interactive_browser.yaml	-
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".	✓	-	CC-BY-SA-4.0 AND LicenseRef-OpenMDW-1.1	litmus_agent.yaml	Nemotron-RL-litmus-bench-v0.2
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	litmus_agent_apptainer.yaml	Nemotron-RL-litmus-bench-v0.2
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.	-	-	-	long_transduction.yaml	-
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.	-	✓	-	longmemeval.yaml	-
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	DAPO17k train problems repeated for trajectory collection with math-verify	Collect rollouts on DAPO17k without training (NeMo RL is_trajectory_collection)	-	✓	-	dapo17k_trajectory_collection.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	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
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
Moldetox	knowledge	MolDeTox toxicity-aware molecular editing verifier	Evaluate toxicity-aware molecular editing with the MolDeTox benchmark	-	✓	-	moldetox.yaml	-
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	-
Nullable Tool Args	agent	Required nullable tool arguments must be JSON null, not the string "None"	-	-	-	-	nullable_tool_args.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	-
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).	-	-	-	openair_congestion.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	-
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	config.yaml	osworld
Over Refusal Detection		-	-	✓	-	TBD	over_refusal_detection.yaml	-
Partner If	instruction_following	Mock-tool variant that grades live tool-calling episodes against instruction-following rubrics, with an example notes backend.	-	-	-	-	mock_tools.yaml	-
Partner If	instruction_following	Text variant that grades a response and its visible evidence against versioned instruction-following rubrics.	-	-	-	-	partner_if.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 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	-	-	-	proof_jury_judge.yaml	-
Proof Verification	math	Proof verification scored against ground truth and meta-verifier agreement	-	-	-	-	proof_verification.yaml	-
R2E Gym		-	-	-	-	-	r2e_gym_example.yaml	-
R2E Gym		-	-	✓	-	MIT (R2E-Gym project license; dataset card unspecified)	r2e_gym_opencode.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
Rna Design	agent	RNA inverse folding: the design tools served over MCP to a harness such as Claude Code.	-	-	-	-	rna_design.yaml	-
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	-
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	-	-	-	ruler2.yaml	-
Scale Swe		-	-	-	-	-	scale_swe_example.yaml	-
Scale Swe		-	-	✓	-	TBD	scale_swe_opencode.yaml	-
Scicode	coding	Multi-step scientific code generation; sub-step solutions executed against SciCode test cases	Improve multi-step scientific code generation	-	-	-	scicode.yaml	-
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.	-	-	-	scicodepile.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	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	bc_v4_8.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	Parallel tool-call verification; the model must emit the expected set of tool calls in a single turn, in any order.	-	-	-	-	parallel_tool_calls_single_step_tool_use_with_argument_comparison.yaml	-
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	-
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.	-	✓	-	spartqa.yaml	-
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.	-	-	-	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	-
String Match	knowledge	General-purpose string matching verifier for free-form text answers	Verify answers via case-insensitive string matching with multiple extraction strategies	-	-	-	string_match.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 Atlas Qa	coding	SWE Atlas Codebase Q&A with the upstream rubric evaluator	-	-	-	-	swe_atlas_qa.yaml	-
Swe Gym		-	-	-	-	-	swe_gym_example.yaml	-
Swe Gym		-	-	✓	-	MIT	swe_gym_opencode.yaml	-
Swe Internal V1		-	-	-	-	-	swe_internal_v1_example.yaml	-
Swe Internal V1		-	-	✓	-	NVIDIA Internal Use Only, Do Not Distribute	swe_internal_v1_opencode.yaml	-
Swe Next		-	-	-	-	-	swe_next_example.yaml	-
Swe Next		-	-	✓	-	MIT	swe_next_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	-
Swe Rebench		-	-	-	-	-	swe_rebench_example.yaml	-
Swe Rebench		-	-	✓	-	Creative Commons Attribution 4.0 International	swe_rebench_opencode.yaml	-
Swemer Oml		-	-	-	-	-	swemer_oml_example.yaml	-
Swemer Oml		-	-	✓	-	NVIDIA Internal Use Only, Do Not Distribute	swemer_oml_opencode.yaml	-
Swemer Ultra		-	-	-	-	-	swemer_ultra_example.yaml	-
Swemer Ultra		-	-	✓	-	NVIDIA Internal Use Only, Do Not Distribute	swemer_ultra_opencode.yaml	-
Swemer V1		-	-	-	-	-	swemer_v1_example.yaml	-
Swemer V1		-	-	✓	-	NVIDIA Internal Use Only, Do Not Distribute	swemer_v1_opencode.yaml	-
Swemer V2		-	-	-	-	-	swemer_v2_example.yaml	-
Swemer V2		-	-	✓	-	NVIDIA Internal Use Only, Do Not Distribute	swemer_v2_opencode.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.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 Bench 4	coding	Official pinned TB4 setup, state, separate verification, and cleanup.	-	-	-	-	terminal_bench_4.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	-
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	vcqa_agent.yaml	vcqa-v1
Verifiers Agent	math	Prime intellect verifiers and environments hub integration, ace-reason math environment example.	Improve math reasoning capabilities.	✓	-	-	verifiers_agent.yaml	-
Verifif	instruction_following	VerifIF instruction following validators with rule-based and LLM judge support	Improve instruction following capabilities with comprehensive validation	-	-	-	verifif.yaml	-
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.	-	-	-	vibench.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	-
Voicebench	e2e	Synthetic text smoke examples for the VoiceBench legacy MCQ scorer	-	-	-	-	voicebench_example.yaml	-
Widesearch	knowledge	Grade structured WideSearch Markdown tables	Evaluate broad web research coverage and accuracy	-	-	-	widesearch.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	-
Wordle	games	Wordle word-guessing game environment for training LLMs	Improve strategic reasoning and letter pattern recognition	✓	✓	Apache 2.0	wordle.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
• Observability - OpenTelemetry traces, metrics, and distributed tracing

🤝 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},
}

⚠️ 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.