> For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.nvidia.com/nemo/evaluator/nightly/tutorials/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/evaluator/_mcp/server. # Available tutorials Step-by-step guides for common workflows. | Tutorial | Description | | ----------------------------------------------------------- | -------------------------------------------------------------------------------------------------- | | [Interactive Walkthrough](/tutorials/walkthrough) | Guided tour of all main features through real config examples — start here. | | [Write Your Own Benchmark](/tutorials/byob) | Define a complete benchmark with `@benchmark` + `@scorer` in under 10 lines. | | [Gym Integration](/tutorials/gym-integration) | Serve benchmarks for NeMo Gym training and consume remote Gym environments. | | [NeMo Skills Integration](/tutorials/skills-integration) | Use NeMo Skills benchmarks with full per-request observability. | | [Legacy Evaluator Containers](/tutorials/legacy-containers) | Run any existing NeMo Evaluator harness container through NEL's unified interface. | | [Distributed Evaluation](/tutorials/distributed-eval) | Scale to thousands of problems with SLURM, Kubernetes, Ray, or manual sharding. | | [Compare Runs](/tutorials/compare) | Diagnose what changed between two runs of the same benchmark with `nel compare`. | | [Config Composition](/tutorials/config-composition) | Reuse config fragments with Hydra-style inheritance and interpolation. | | [Quality Gates](/tutorials/quality-gate) | Turn benchmark thresholds into a suite-level `GO / NO-GO / INCONCLUSIVE` decision with `nel gate`. | | [External Environments](/tutorials/adapters) | Connect Gym, NeMo Skills, and lm-eval environments through the unified registry. |