[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6XGD33SMXZEHAJRX3FP4BW4":3,"skill-same:01M6XGD33SMXZEHAJRX3FP4BW4":105},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":26,"publishedAt":47,"linkOnly":48,"markdownContent":49,"markdownBody":50,"frontMatter":51,"refName":67,"commitSha":68,"skillDirectory":69,"forksCount":14,"repositoryHtmlUrl":70,"repositoryHomepageUrl":6,"ownerHtmlUrl":71,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":72,"install":73,"resources":86},"01M6XGD33SMXZEHAJRX3FP4BW4","nemo-evaluator-sdk",null,"Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.","fadrienne\u002FMyGitHub","fadrienne","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F197874571?v=4","01M6X64V8VWCRSMFZ4EPS2BWXG","Francesca Adrienne","01M6X64VD5MW4F9PHDWQKS7ZAF",0,"MIT","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fopenscience\u002Fbackend\u002Fcli\u002Fskills\u002Fml-training\u002Fnemo-evaluator\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000010","后端与接口","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000011","运维与部署",[27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46],"sdk","nemo evaluator","NeMo","nemo evaluator sdk","evaluator","when","llms","hpc","harnesses","Scalable","synthetic","local","across","launcher","Safety","HumanEval","Evaluation","training","benchmarking","architecture","2026-11-10 10:12:30",false,"---\nname: nemo-evaluator-sdk\ndescription: Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.\ncategory: ml-training\nversion: 1.0.0\nauthor: Synthetic Sciences\nlicense: MIT\ntags: [Evaluation, NeMo, NVIDIA, Benchmarking, MMLU, HumanEval, Multi-Backend, Slurm, Docker, Reproducible, Enterprise]\ndependencies: [nemo-evaluator-launcher>=0.1.25, docker]\n---\n\n# NeMo Evaluator SDK - Enterprise LLM Benchmarking\n\n## Quick Start\n\nNeMo Evaluator SDK evaluates LLMs across 100+ benchmarks from 18+ harnesses using containerized, reproducible evaluation with multi-backend execution (local Docker, Slurm HPC, Lepton cloud).\n\n**Installation**:\n```bash\npip install nemo-evaluator-launcher\n```\n\n**Set API key and run evaluation**:\n```bash\nexport NGC_API_KEY=nvapi-your-key-here\n\n# Create minimal config\ncat > config.yaml \u003C\u003C 'EOF'\ndefaults:\n  - execution: local\n  - deployment: none\n  - _self_\n\nexecution:\n  output_dir: .\u002Fresults\n\ntarget:\n  api_endpoint:\n    model_id: meta\u002Fllama-3.1-8b-instruct\n    url: https:\u002F\u002Fintegrate.api.nvidia.com\u002Fv1\u002Fchat\u002Fcompletions\n    api_key_name: NGC_API_KEY\n\nevaluation:\n  tasks:\n    - name: ifeval\nEOF\n\n# Run evaluation\nnemo-evaluator-launcher run --config-dir . --config-name config\n```\n\n**View available tasks**:\n```bash\nnemo-evaluator-launcher ls tasks\n```\n\n## Common Workflows\n\n### Workflow 1: Evaluate Model on Standard Benchmarks\n\nRun core academic benchmarks (MMLU, GSM8K, IFEval) on any OpenAI-compatible endpoint.\n\n**Checklist**:\n```\nStandard Evaluation:\n- [ ] Step 1: Configure API endpoint\n- [ ] Step 2: Select benchmarks\n- [ ] Step 3: Run evaluation\n- [ ] Step 4: Check results\n```\n\n**Step 1: Configure API endpoint**\n\n```yaml\n# config.yaml\ndefaults:\n  - execution: local\n  - deployment: none\n  - _self_\n\nexecution:\n  output_dir: .\u002Fresults\n\ntarget:\n  api_endpoint:\n    model_id: meta\u002Fllama-3.1-8b-instruct\n    url: https:\u002F\u002Fintegrate.api.nvidia.com\u002Fv1\u002Fchat\u002Fcompletions\n    api_key_name: NGC_API_KEY\n```\n\nFor self-hosted endpoints (vLLM, TRT-LLM):\n```yaml\ntarget:\n  api_endpoint:\n    model_id: my-model\n    url: http:\u002F\u002Flocalhost:8000\u002Fv1\u002Fchat\u002Fcompletions\n    api_key_name: \"\"  # No key needed for local\n```\n\n**Step 2: Select benchmarks**\n\nAdd tasks to your config:\n```yaml\nevaluation:\n  tasks:\n    - name: ifeval           # Instruction following\n    - name: gpqa_diamond     # Graduate-level QA\n      env_vars:\n        HF_TOKEN: HF_TOKEN   # Some tasks need HF token\n    - name: gsm8k_cot_instruct  # Math reasoning\n    - name: humaneval        # Code generation\n```\n\n**Step 3: Run evaluation**\n\n```bash\n# Run with config file\nnemo-evaluator-launcher run \\\n  --config-dir . \\\n  --config-name config\n\n# Override output directory\nnemo-evaluator-launcher run \\\n  --config-dir . \\\n  --config-name config \\\n  -o execution.output_dir=.\u002Fmy_results\n\n# Limit samples for quick testing\nnemo-evaluator-launcher run \\\n  --config-dir . \\\n  --config-name config \\\n  -o +evaluation.nemo_evaluator_config.config.params.limit_samples=10\n```\n\n**Step 4: Check results**\n\n```bash\n# Check job status\nnemo-evaluator-launcher status \u003Cinvocation_id>\n\n# List all runs\nnemo-evaluator-launcher ls runs\n\n# View results\ncat results\u002F\u003Cinvocation_id>\u002F\u003Ctask>\u002Fartifacts\u002Fresults.yml\n```\n\n### Workflow 2: Run Evaluation on Slurm HPC Cluster\n\nExecute large-scale evaluation on HPC infrastructure.\n\n**Checklist**:\n```\nSlurm Evaluation:\n- [ ] Step 1: Configure Slurm settings\n- [ ] Step 2: Set up model deployment\n- [ ] Step 3: Launch evaluation\n- [ ] Step 4: Monitor job status\n```\n\n**Step 1: Configure Slurm settings**\n\n```yaml\n# slurm_config.yaml\ndefaults:\n  - execution: slurm\n  - deployment: vllm\n  - _self_\n\nexecution:\n  hostname: cluster.example.com\n  account: my_slurm_account\n  partition: gpu\n  output_dir: \u002Fshared\u002Fresults\n  walltime: \"04:00:00\"\n  nodes: 1\n  gpus_per_node: 8\n```\n\n**Step 2: Set up model deployment**\n\n```yaml\ndeployment:\n  checkpoint_path: \u002Fshared\u002Fmodels\u002Fllama-3.1-8b\n  tensor_parallel_size: 2\n  data_parallel_size: 4\n  max_model_len: 4096\n\ntarget:\n  api_endpoint:\n    model_id: llama-3.1-8b\n    # URL auto-generated by deployment\n```\n\n**Step 3: Launch evaluation**\n\n```bash\nnemo-evaluator-launcher run \\\n  --config-dir . \\\n  --config-name slurm_config\n```\n\n**Step 4: Monitor job status**\n\n```bash\n# Check status (queries sacct)\nnemo-evaluator-launcher status \u003Cinvocation_id>\n\n# View detailed info\nnemo-evaluator-launcher info \u003Cinvocation_id>\n\n# Kill if needed\nnemo-evaluator-launcher kill \u003Cinvocation_id>\n```\n\n### Workflow 3: Compare Multiple Models\n\nBenchmark multiple models on the same tasks for comparison.\n\n**Checklist**:\n```\nModel Comparison:\n- [ ] Step 1: Create base config\n- [ ] Step 2: Run evaluations with overrides\n- [ ] Step 3: Export and compare results\n```\n\n**Step 1: Create base config**\n\n```yaml\n# base_eval.yaml\ndefaults:\n  - execution: local\n  - deployment: none\n  - _self_\n\nexecution:\n  output_dir: .\u002Fcomparison_results\n\nevaluation:\n  nemo_evaluator_config:\n    config:\n      params:\n        temperature: 0.01\n        parallelism: 4\n  tasks:\n    - name: mmlu_pro\n    - name: gsm8k_cot_instruct\n    - name: ifeval\n```\n\n**Step 2: Run evaluations with model overrides**\n\n```bash\n# Evaluate Llama 3.1 8B\nnemo-evaluator-launcher run \\\n  --config-dir . \\\n  --config-name base_eval \\\n  -o target.api_endpoint.model_id=meta\u002Fllama-3.1-8b-instruct \\\n  -o target.api_endpoint.url=https:\u002F\u002Fintegrate.api.nvidia.com\u002Fv1\u002Fchat\u002Fcompletions\n\n# Evaluate Mistral 7B\nnemo-evaluator-launcher run \\\n  --config-dir . \\\n  --config-name base_eval \\\n  -o target.api_endpoint.model_id=mistralai\u002Fmistral-7b-instruct-v0.3 \\\n  -o target.api_endpoint.url=https:\u002F\u002Fintegrate.api.nvidia.com\u002Fv1\u002Fchat\u002Fcompletions\n```\n\n**Step 3: Export and compare**\n\n```bash\n# Export to MLflow\nnemo-evaluator-launcher export \u003Cinvocation_id_1> --dest mlflow\nnemo-evaluator-launcher export \u003Cinvocation_id_2> --dest mlflow\n\n# Export to local JSON\nnemo-evaluator-launcher export \u003Cinvocation_id> --dest local --format json\n\n# Export to Weights & Biases\nnemo-evaluator-launcher export \u003Cinvocation_id> --dest wandb\n```\n\n### Workflow 4: Safety and Vision-Language Evaluation\n\nEvaluate models on safety benchmarks and VLM tasks.\n\n**Checklist**:\n```\nSafety\u002FVLM Evaluation:\n- [ ] Step 1: Configure safety tasks\n- [ ] Step 2: Set up VLM tasks (if applicable)\n- [ ] Step 3: Run evaluation\n```\n\n**Step 1: Configure safety tasks**\n\n```yaml\nevaluation:\n  tasks:\n    - name: aegis              # Safety harness\n    - name: wildguard          # Safety classification\n    - name: garak              # Security probing\n```\n\n**Step 2: Configure VLM tasks**\n\n```yaml\n# For vision-language models\ntarget:\n  api_endpoint:\n    type: vlm  # Vision-language endpoint\n    model_id: nvidia\u002Fllama-3.2-90b-vision-instruct\n    url: https:\u002F\u002Fintegrate.api.nvidia.com\u002Fv1\u002Fchat\u002Fcompletions\n\nevaluation:\n  tasks:\n    - name: ocrbench           # OCR evaluation\n    - name: chartqa            # Chart understanding\n    - name: mmmu               # Multimodal understanding\n```\n\n## When to Use vs Alternatives\n\n**Use NeMo Evaluator when:**\n- Need **100+ benchmarks** from 18+ harnesses in one platform\n- Running evaluations on **Slurm HPC clusters** or cloud\n- Requiring **reproducible** containerized evaluation\n- Evaluating against **OpenAI-compatible APIs** (vLLM, TRT-LLM, NIMs)\n- Need **enterprise-grade** evaluation with result export (MLflow, W&B)\n\n**Use alternatives instead:**\n- **lm-evaluation-harness**: Simpler setup for quick local evaluation\n- **bigcode-evaluation-harness**: Focused only on code benchmarks\n- **HELM**: Stanford's broader evaluation (fairness, efficiency)\n- **Custom scripts**: Highly specialized domain evaluation\n\n## Supported Harnesses and Tasks\n\n| Harness | Task Count | Categories |\n|---------|-----------|------------|\n| `lm-evaluation-harness` | 60+ | MMLU, GSM8K, HellaSwag, ARC |\n| `simple-evals` | 20+ | GPQA, MATH, AIME |\n| `bigcode-evaluation-harness` | 25+ | HumanEval, MBPP, MultiPL-E |\n| `safety-harness` | 3 | Aegis, WildGuard |\n| `garak` | 1 | Security probing |\n| `vlmevalkit` | 6+ | OCRBench, ChartQA, MMMU |\n| `bfcl` | 6 | Function calling v2\u002Fv3 |\n| `mtbench` | 2 | Multi-turn conversation |\n| `livecodebench` | 10+ | Live coding evaluation |\n| `helm` | 15 | Medical domain |\n| `nemo-skills` | 8 | Math, science, agentic |\n\n## Common Issues\n\n**Issue: Container pull fails**\n\nEnsure NGC credentials are configured:\n```bash\ndocker login nvcr.io -u '$oauthtoken' -p $NGC_API_KEY\n```\n\n**Issue: Task requires environment variable**\n\nSome tasks need HF_TOKEN or JUDGE_API_KEY:\n```yaml\nevaluation:\n  tasks:\n    - name: gpqa_diamond\n      env_vars:\n        HF_TOKEN: HF_TOKEN  # Maps env var name to env var\n```\n\n**Issue: Evaluation timeout**\n\nIncrease parallelism or reduce samples:\n```bash\n-o +evaluation.nemo_evaluator_config.config.params.parallelism=8\n-o +evaluation.nemo_evaluator_config.config.params.limit_samples=100\n```\n\n**Issue: Slurm job not starting**\n\nCheck Slurm account and partition:\n```yaml\nexecution:\n  account: correct_account\n  partition: gpu\n  qos: normal  # May need specific QOS\n```\n\n**Issue: Different results than expected**\n\nVerify configuration matches reported settings:\n```yaml\nevaluation:\n  nemo_evaluator_config:\n    config:\n      params:\n        temperature: 0.0  # Deterministic\n        num_fewshot: 5    # Check paper's fewshot count\n```\n\n## CLI Reference\n\n| Command | Description |\n|---------|-------------|\n| `run` | Execute evaluation with config |\n| `status \u003Cid>` | Check job status |\n| `info \u003Cid>` | View detailed job info |\n| `ls tasks` | List available benchmarks |\n| `ls runs` | List all invocations |\n| `export \u003Cid>` | Export results (mlflow\u002Fwandb\u002Flocal) |\n| `kill \u003Cid>` | Terminate running job |\n\n## Configuration Override Examples\n\n```bash\n# Override model endpoint\n-o target.api_endpoint.model_id=my-model\n-o target.api_endpoint.url=http:\u002F\u002Flocalhost:8000\u002Fv1\u002Fchat\u002Fcompletions\n\n# Add evaluation parameters\n-o +evaluation.nemo_evaluator_config.config.params.temperature=0.5\n-o +evaluation.nemo_evaluator_config.config.params.parallelism=8\n-o +evaluation.nemo_evaluator_config.config.params.limit_samples=50\n\n# Change execution settings\n-o execution.output_dir=\u002Fcustom\u002Fpath\n-o execution.mode=parallel\n\n# Dynamically set tasks\n-o 'evaluation.tasks=[{name: ifeval}, {name: gsm8k}]'\n```\n\n## Python API Usage\n\nFor programmatic evaluation without the CLI:\n\n```python\nfrom nemo_evaluator.core.evaluate import evaluate\nfrom nemo_evaluator.api.api_dataclasses import (\n    EvaluationConfig,\n    EvaluationTarget,\n    ApiEndpoint,\n    EndpointType,\n    ConfigParams\n)\n\n# Configure evaluation\neval_config = EvaluationConfig(\n    type=\"mmlu_pro\",\n    output_dir=\".\u002Fresults\",\n    params=ConfigParams(\n        limit_samples=10,\n        temperature=0.0,\n        max_new_tokens=1024,\n        parallelism=4\n    )\n)\n\n# Configure target endpoint\ntarget_config = EvaluationTarget(\n    api_endpoint=ApiEndpoint(\n        model_id=\"meta\u002Fllama-3.1-8b-instruct\",\n        url=\"https:\u002F\u002Fintegrate.api.nvidia.com\u002Fv1\u002Fchat\u002Fcompletions\",\n        type=EndpointType.CHAT,\n        api_key=\"nvapi-your-key-here\"\n    )\n)\n\n# Run evaluation\nresult = evaluate(eval_cfg=eval_config, target_cfg=target_config)\n```\n\n## Advanced Topics\n\n**Multi-backend execution**: See [references\u002Fexecution-backends.md](references\u002Fexecution-backends.md)\n**Configuration deep-dive**: See [references\u002Fconfiguration.md](references\u002Fconfiguration.md)\n**Adapter and interceptor system**: See [references\u002Fadapter-system.md](references\u002Fadapter-system.md)\n**Custom benchmark integration**: See [references\u002Fcustom-benchmarks.md](references\u002Fcustom-benchmarks.md)\n\n## Requirements\n\n- **Python**: 3.10-3.13\n- **Docker**: Required for local execution\n- **NGC API Key**: For pulling containers and using NVIDIA Build\n- **HF_TOKEN**: Required for some benchmarks (GPQA, MMLU)\n\n## Resources\n\n- **GitHub**: https:\u002F\u002Fgithub.com\u002FNVIDIA-NeMo\u002FEvaluator\n- **NGC Containers**: nvcr.io\u002Fnvidia\u002Feval-factory\u002F\n- **NVIDIA Build**: https:\u002F\u002Fbuild.nvidia.com (free hosted models)\n- **Documentation**: https:\u002F\u002Fgithub.com\u002FNVIDIA-NeMo\u002FEvaluator\u002Ftree\u002Fmain\u002Fdocs\n","# NeMo Evaluator SDK - Enterprise LLM Benchmarking\n\n## Quick Start\n\nNeMo Evaluator SDK evaluates LLMs across 100+ benchmarks from 18+ harnesses using containerized, reproducible evaluation with multi-backend execution (local Docker, Slurm HPC, Lepton cloud).\n\n**Installation**:\n```bash\npip install nemo-evaluator-launcher\n```\n\n**Set API key and run evaluation**:\n```bash\nexport NGC_API_KEY=nvapi-your-key-here\n\n# Create minimal config\ncat > config.yaml \u003C\u003C 'EOF'\ndefaults:\n  - execution: local\n  - deployment: none\n  - _self_\n\nexecution:\n  output_dir: .\u002Fresults\n\ntarget:\n  api_endpoint:\n    model_id: meta\u002Fllama-3.1-8b-instruct\n    url: https:\u002F\u002Fintegrate.api.nvidia.com\u002Fv1\u002Fchat\u002Fcompletions\n    api_key_name: NGC_API_KEY\n\nevaluation:\n  tasks:\n    - name: ifeval\nEOF\n\n# Run evaluation\nnemo-evaluator-launcher run --config-dir . --config-name config\n```\n\n**View available tasks**:\n```bash\nnemo-evaluator-launcher ls tasks\n```\n\n## Common Workflows\n\n### Workflow 1: Evaluate Model on Standard Benchmarks\n\nRun core academic benchmarks (MMLU, GSM8K, IFEval) on any OpenAI-compatible endpoint.\n\n**Checklist**:\n```\nStandard Evaluation:\n- [ ] Step 1: Configure API endpoint\n- [ ] Step 2: Select benchmarks\n- [ ] Step 3: Run evaluation\n- [ ] Step 4: Check results\n```\n\n**Step 1: Configure API endpoint**\n\n```yaml\n# config.yaml\ndefaults:\n  - execution: local\n  - deployment: none\n  - _self_\n\nexecution:\n  output_dir: .\u002Fresults\n\ntarget:\n  api_endpoint:\n    model_id: meta\u002Fllama-3.1-8b-instruct\n    url: https:\u002F\u002Fintegrate.api.nvidia.com\u002Fv1\u002Fchat\u002Fcompletions\n    api_key_name: NGC_API_KEY\n```\n\nFor self-hosted endpoints (vLLM, TRT-LLM):\n```yaml\ntarget:\n  api_endpoint:\n    model_id: my-model\n    url: http:\u002F\u002Flocalhost:8000\u002Fv1\u002Fchat\u002Fcompletions\n    api_key_name: \"\"  # No key needed for local\n```\n\n**Step 2: Select benchmarks**\n\nAdd tasks to your config:\n```yaml\nevaluation:\n  tasks:\n    - name: ifeval           # Instruction following\n    - name: gpqa_diamond     # Graduate-level QA\n      env_vars:\n        HF_TOKEN: HF_TOKEN   # Some tasks need HF token\n    - name: gsm8k_cot_instruct  # Math reasoning\n    - name: humaneval        # Code generation\n```\n\n**Step 3: Run evaluation**\n\n```bash\n# Run with config file\nnemo-evaluator-launcher run \\\n  --config-dir . \\\n  --config-name config\n\n# Override output directory\nnemo-evaluator-launcher run \\\n  --config-dir . \\\n  --config-name config \\\n  -o execution.output_dir=.\u002Fmy_results\n\n# Limit samples for quick testing\nnemo-evaluator-launcher run \\\n  --config-dir . \\\n  --config-name config \\\n  -o +evaluation.nemo_evaluator_config.config.params.limit_samples=10\n```\n\n**Step 4: Check results**\n\n```bash\n# Check job status\nnemo-evaluator-launcher status \u003Cinvocation_id>\n\n# List all runs\nnemo-evaluator-launcher ls runs\n\n# View results\ncat results\u002F\u003Cinvocation_id>\u002F\u003Ctask>\u002Fartifacts\u002Fresults.yml\n```\n\n### Workflow 2: Run Evaluation on Slurm HPC Cluster\n\nExecute large-scale evaluation on HPC infrastructure.\n\n**Checklist**:\n```\nSlurm Evaluation:\n- [ ] Step 1: Configure Slurm settings\n- [ ] Step 2: Set up model deployment\n- [ ] Step 3: Launch evaluation\n- [ ] Step 4: Monitor job status\n```\n\n**Step 1: Configure Slurm settings**\n\n```yaml\n# slurm_config.yaml\ndefaults:\n  - execution: slurm\n  - deployment: vllm\n  - _self_\n\nexecution:\n  hostname: cluster.example.com\n  account: my_slurm_account\n  partition: gpu\n  output_dir: \u002Fshared\u002Fresults\n  walltime: \"04:00:00\"\n  nodes: 1\n  gpus_per_node: 8\n```\n\n**Step 2: Set up model deployment**\n\n```yaml\ndeployment:\n  checkpoint_path: \u002Fshared\u002Fmodels\u002Fllama-3.1-8b\n  tensor_parallel_size: 2\n  data_parallel_size: 4\n  max_model_len: 4096\n\ntarget:\n  api_endpoint:\n    model_id: llama-3.1-8b\n    # URL auto-generated by deployment\n```\n\n**Step 3: Launch evaluation**\n\n```bash\nnemo-evaluator-launcher run \\\n  --config-dir . \\\n  --config-name slurm_config\n```\n\n**Step 4: Monitor job status**\n\n```bash\n# Check status (queries sacct)\nnemo-evaluator-launcher status \u003Cinvocation_id>\n\n# View detailed info\nnemo-evaluator-launcher info \u003Cinvocation_id>\n\n# Kill if needed\nnemo-evaluator-launcher kill \u003Cinvocation_id>\n```\n\n### Workflow 3: Compare Multiple Models\n\nBenchmark multiple models on the same tasks for comparison.\n\n**Checklist**:\n```\nModel Comparison:\n- [ ] Step 1: Create base config\n- [ ] Step 2: Run evaluations with overrides\n- [ ] Step 3: Export and compare results\n```\n\n**Step 1: Create base config**\n\n```yaml\n# base_eval.yaml\ndefaults:\n  - execution: local\n  - deployment: none\n  - _self_\n\nexecution:\n  output_dir: .\u002Fcomparison_results\n\nevaluation:\n  nemo_evaluator_config:\n    config:\n      params:\n        temperature: 0.01\n        parallelism: 4\n  tasks:\n    - name: mmlu_pro\n    - name: gsm8k_cot_instruct\n    - name: ifeval\n```\n\n**Step 2: Run evaluations with model overrides**\n\n```bash\n# Evaluate Llama 3.1 8B\nnemo-evaluator-launcher run \\\n  --config-dir . \\\n  --config-name base_eval \\\n  -o target.api_endpoint.model_id=meta\u002Fllama-3.1-8b-instruct \\\n  -o target.api_endpoint.url=https:\u002F\u002Fintegrate.api.nvidia.com\u002Fv1\u002Fchat\u002Fcompletions\n\n# Evaluate Mistral 7B\nnemo-evaluator-launcher run \\\n  --config-dir . \\\n  --config-name base_eval \\\n  -o target.api_endpoint.model_id=mistralai\u002Fmistral-7b-instruct-v0.3 \\\n  -o target.api_endpoint.url=https:\u002F\u002Fintegrate.api.nvidia.com\u002Fv1\u002Fchat\u002Fcompletions\n```\n\n**Step 3: Export and compare**\n\n```bash\n# Export to MLflow\nnemo-evaluator-launcher export \u003Cinvocation_id_1> --dest mlflow\nnemo-evaluator-launcher export \u003Cinvocation_id_2> --dest mlflow\n\n# Export to local JSON\nnemo-evaluator-launcher export \u003Cinvocation_id> --dest local --format json\n\n# Export to Weights & Biases\nnemo-evaluator-launcher export \u003Cinvocation_id> --dest wandb\n```\n\n### Workflow 4: Safety and Vision-Language Evaluation\n\nEvaluate models on safety benchmarks and VLM tasks.\n\n**Checklist**:\n```\nSafety\u002FVLM Evaluation:\n- [ ] Step 1: Configure safety tasks\n- [ ] Step 2: Set up VLM tasks (if applicable)\n- [ ] Step 3: Run evaluation\n```\n\n**Step 1: Configure safety tasks**\n\n```yaml\nevaluation:\n  tasks:\n    - name: aegis              # Safety harness\n    - name: wildguard          # Safety classification\n    - name: garak              # Security probing\n```\n\n**Step 2: Configure VLM tasks**\n\n```yaml\n# For vision-language models\ntarget:\n  api_endpoint:\n    type: vlm  # Vision-language endpoint\n    model_id: nvidia\u002Fllama-3.2-90b-vision-instruct\n    url: https:\u002F\u002Fintegrate.api.nvidia.com\u002Fv1\u002Fchat\u002Fcompletions\n\nevaluation:\n  tasks:\n    - name: ocrbench           # OCR evaluation\n    - name: chartqa            # Chart understanding\n    - name: mmmu               # Multimodal understanding\n```\n\n## When to Use vs Alternatives\n\n**Use NeMo Evaluator when:**\n- Need **100+ benchmarks** from 18+ harnesses in one platform\n- Running evaluations on **Slurm HPC clusters** or cloud\n- Requiring **reproducible** containerized evaluation\n- Evaluating against **OpenAI-compatible APIs** (vLLM, TRT-LLM, NIMs)\n- Need **enterprise-grade** evaluation with result export (MLflow, W&B)\n\n**Use alternatives instead:**\n- **lm-evaluation-harness**: Simpler setup for quick local evaluation\n- **bigcode-evaluation-harness**: Focused only on code benchmarks\n- **HELM**: Stanford's broader evaluation (fairness, efficiency)\n- **Custom scripts**: Highly specialized domain evaluation\n\n## Supported Harnesses and Tasks\n\n| Harness | Task Count | Categories |\n|---------|-----------|------------|\n| `lm-evaluation-harness` | 60+ | MMLU, GSM8K, HellaSwag, ARC |\n| `simple-evals` | 20+ | GPQA, MATH, AIME |\n| `bigcode-evaluation-harness` | 25+ | HumanEval, MBPP, MultiPL-E |\n| `safety-harness` | 3 | Aegis, WildGuard |\n| `garak` | 1 | Security probing |\n| `vlmevalkit` | 6+ | OCRBench, ChartQA, MMMU |\n| `bfcl` | 6 | Function calling v2\u002Fv3 |\n| `mtbench` | 2 | Multi-turn conversation |\n| `livecodebench` | 10+ | Live coding evaluation |\n| `helm` | 15 | Medical domain |\n| `nemo-skills` | 8 | Math, science, agentic |\n\n## Common Issues\n\n**Issue: Container pull fails**\n\nEnsure NGC credentials are configured:\n```bash\ndocker login nvcr.io -u '$oauthtoken' -p $NGC_API_KEY\n```\n\n**Issue: Task requires environment variable**\n\nSome tasks need HF_TOKEN or JUDGE_API_KEY:\n```yaml\nevaluation:\n  tasks:\n    - name: gpqa_diamond\n      env_vars:\n        HF_TOKEN: HF_TOKEN  # Maps env var name to env var\n```\n\n**Issue: Evaluation timeout**\n\nIncrease parallelism or reduce samples:\n```bash\n-o +evaluation.nemo_evaluator_config.config.params.parallelism=8\n-o +evaluation.nemo_evaluator_config.config.params.limit_samples=100\n```\n\n**Issue: Slurm job not starting**\n\nCheck Slurm account and partition:\n```yaml\nexecution:\n  account: correct_account\n  partition: gpu\n  qos: normal  # May need specific QOS\n```\n\n**Issue: Different results than expected**\n\nVerify configuration matches reported settings:\n```yaml\nevaluation:\n  nemo_evaluator_config:\n    config:\n      params:\n        temperature: 0.0  # Deterministic\n        num_fewshot: 5    # Check paper's fewshot count\n```\n\n## CLI Reference\n\n| Command | Description |\n|---------|-------------|\n| `run` | Execute evaluation with config |\n| `status \u003Cid>` | Check job status |\n| `info \u003Cid>` | View detailed job info |\n| `ls tasks` | List available benchmarks |\n| `ls runs` | List all invocations |\n| `export \u003Cid>` | Export results (mlflow\u002Fwandb\u002Flocal) |\n| `kill \u003Cid>` | Terminate running job |\n\n## Configuration Override Examples\n\n```bash\n# Override model endpoint\n-o target.api_endpoint.model_id=my-model\n-o target.api_endpoint.url=http:\u002F\u002Flocalhost:8000\u002Fv1\u002Fchat\u002Fcompletions\n\n# Add evaluation parameters\n-o +evaluation.nemo_evaluator_config.config.params.temperature=0.5\n-o +evaluation.nemo_evaluator_config.config.params.parallelism=8\n-o +evaluation.nemo_evaluator_config.config.params.limit_samples=50\n\n# Change execution settings\n-o execution.output_dir=\u002Fcustom\u002Fpath\n-o execution.mode=parallel\n\n# Dynamically set tasks\n-o 'evaluation.tasks=[{name: ifeval}, {name: gsm8k}]'\n```\n\n## Python API Usage\n\nFor programmatic evaluation without the CLI:\n\n```python\nfrom nemo_evaluator.core.evaluate import evaluate\nfrom nemo_evaluator.api.api_dataclasses import (\n    EvaluationConfig,\n    EvaluationTarget,\n    ApiEndpoint,\n    EndpointType,\n    ConfigParams\n)\n\n# Configure evaluation\neval_config = EvaluationConfig(\n    type=\"mmlu_pro\",\n    output_dir=\".\u002Fresults\",\n    params=ConfigParams(\n        limit_samples=10,\n        temperature=0.0,\n        max_new_tokens=1024,\n        parallelism=4\n    )\n)\n\n# Configure target endpoint\ntarget_config = EvaluationTarget(\n    api_endpoint=ApiEndpoint(\n        model_id=\"meta\u002Fllama-3.1-8b-instruct\",\n        url=\"https:\u002F\u002Fintegrate.api.nvidia.com\u002Fv1\u002Fchat\u002Fcompletions\",\n        type=EndpointType.CHAT,\n        api_key=\"nvapi-your-key-here\"\n    )\n)\n\n# Run evaluation\nresult = evaluate(eval_cfg=eval_config, target_cfg=target_config)\n```\n\n## Advanced Topics\n\n**Multi-backend execution**: See [references\u002Fexecution-backends.md](references\u002Fexecution-backends.md)\n**Configuration deep-dive**: See [references\u002Fconfiguration.md](references\u002Fconfiguration.md)\n**Adapter and interceptor system**: See [references\u002Fadapter-system.md](references\u002Fadapter-system.md)\n**Custom benchmark integration**: See [references\u002Fcustom-benchmarks.md](references\u002Fcustom-benchmarks.md)\n\n## Requirements\n\n- **Python**: 3.10-3.13\n- **Docker**: Required for local execution\n- **NGC API Key**: For pulling containers and using NVIDIA Build\n- **HF_TOKEN**: Required for some benchmarks (GPQA, MMLU)\n\n## Resources\n\n- **GitHub**: https:\u002F\u002Fgithub.com\u002FNVIDIA-NeMo\u002FEvaluator\n- **NGC Containers**: nvcr.io\u002Fnvidia\u002Feval-factory\u002F\n- **NVIDIA Build**: https:\u002F\u002Fbuild.nvidia.com (free hosted models)\n- **Documentation**: https:\u002F\u002Fgithub.com\u002FNVIDIA-NeMo\u002FEvaluator\u002Ftree\u002Fmain\u002Fdocs\n",{"name":5,"tags":52,"author":61,"license":15,"version":62,"category":63,"description":7,"dependencies":64},[43,29,53,54,55,42,56,57,58,59,60],"NVIDIA","Benchmarking","MMLU","Multi-Backend","Slurm","Docker","Reproducible","Enterprise","Synthetic Sciences","1.0.0","ml-training",[65,66],"nemo-evaluator-launcher>=0.1.25","docker","main","4aa39efd1cdab0b4657ecee16c92a92011a5b10f","openscience\u002Fbackend\u002Fcli\u002Fskills\u002Fml-training\u002Fnemo-evaluator","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub","https:\u002F\u002Fgithub.com\u002Ffadrienne","2026-10-28 00:43:09",{"source":8,"skillName":5,"commands":74,"prompt":84,"zipAvailable":85},[75,78,81],{"tool":76,"command":77},"npx","npx skills add fadrienne\u002FMyGitHub --skill nemo-evaluator-sdk",{"tool":79,"command":80},"bunx","bunx skills add fadrienne\u002FMyGitHub --skill nemo-evaluator-sdk",{"tool":82,"command":83},"pnpm","pnpm dlx skills add fadrienne\u002FMyGitHub --skill nemo-evaluator-sdk","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fopenscience\u002Fbackend\u002Fcli\u002Fskills\u002Fml-training\u002Fnemo-evaluator\u002FSKILL.md",true,[87,93,97,101],{"path":88,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":91,"sourceHtmlUrl":92},"references\u002Fadapter-system.md","REFERENCE","参考文档",9468,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fopenscience\u002Fbackend\u002Fcli\u002Fskills\u002Fml-training\u002Fnemo-evaluator\u002Freferences\u002Fadapter-system.md",{"path":94,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":95,"sourceHtmlUrl":96},"references\u002Fconfiguration.md",9567,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fopenscience\u002Fbackend\u002Fcli\u002Fskills\u002Fml-training\u002Fnemo-evaluator\u002Freferences\u002Fconfiguration.md",{"path":98,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":99,"sourceHtmlUrl":100},"references\u002Fcustom-benchmarks.md",7101,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fopenscience\u002Fbackend\u002Fcli\u002Fskills\u002Fml-training\u002Fnemo-evaluator\u002Freferences\u002Fcustom-benchmarks.md",{"path":102,"resourceType":89,"resourceTypeDesc":90,"sizeBytes":103,"sourceHtmlUrl":104},"references\u002Fexecution-backends.md",9351,"https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fopenscience\u002Fbackend\u002Fcli\u002Fskills\u002Fml-training\u002Fnemo-evaluator\u002Freferences\u002Fexecution-backends.md",[106,135,162,196,223,250],{"skillNo":107,"name":108,"nameZh":6,"description":109,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":110,"categories":111,"keywords":115,"publishedAt":47},"01M7167B28PK20HP7R7ZED2DY0","statistical-power","Sample size calculation, power analysis, and effect size conversion for scientific studies. Use BEFORE data collection (a priori) to determine required N, or after (post-hoc) to compute achieved power. Covers parametric tests (t-test, ANOVA, chi-square, proportions, correlation, regression), simulation-based power for complex\u002Fclustered\u002Fnested designs, and power curves. Use this skill when someone asks 'how many samples do I need', 'what is my power', 'what effect size can I detect', or any variant. Pairs with \u002Fexperimental-design (choose design first, then compute power) and \u002Fstatistical-analysis (analyze data after collection).","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fscientific-agent-skills\u002Fskills\u002Fstatistical-power\u002FSKILL.md",[112],{"categoryNo":113,"categoryName":114,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[116,117,118,119,120,121,122,123,32,124,125,126,127,128,129,130,131,132,133,134],"power","statistical power","effect","scipy","regression","choose","design","uv","Bash","collection","analysis","calculation","ANOVA","conversion","analyze","t-test","chi-square","simulation","sample",{"skillNo":136,"name":137,"nameZh":6,"description":138,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":139,"categories":140,"keywords":144,"publishedAt":47},"01M71677EBCM8EPCE9BZCK8505","statistical-analysis","Guided statistical analysis with test selection and reporting. Use when you need help choosing appropriate tests for your data, assumption checking, power analysis, and APA-formatted results. Best for academic research reporting, test selection guidance. For implementing specific models programmatically use statsmodels.","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fscientific-agent-skills\u002Fskills\u002Fstatistical-analysis\u002FSKILL.md",[141],{"categoryNo":142,"categoryName":143,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",[126,145,116,146,147,148,32,149,150,151,152,153,154,155,156,157,158,159,160,161],"statistical analysis","academic research","implementing","selection","you","reporting","data","for","tests","use","with","test","research","results","statsmodels","models","help",{"skillNo":163,"name":164,"nameZh":6,"description":165,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":166,"categories":167,"keywords":177,"publishedAt":47},"01M71673R93XAHFH81DBNVNG7H","scientific-writing","Core skill for the deep research and writing tool. Write scientific manuscripts in full paragraphs (never bullet points). Use two-stage process with (1) section outlines with key points using research-lookup then (2) convert to flowing prose. IMRAD structure, citations (APA\u002FAMA\u002FVancouver), figures\u002Ftables, reporting guidelines (CONSORT\u002FSTROBE\u002FPRISMA), for research papers and journal submissions.","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fscientific-agent-skills\u002Fskills\u002Fscientific-writing\u002FSKILL.md",[168,171,172],{"categoryNo":169,"categoryName":170,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",{"categoryNo":113,"categoryName":114,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":173,"categoryName":174,"taxonomyType":175,"taxonomyTypeDesc":176},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[178,179,180,181,182,183,184,185,186,187,124,188,189,190,191,192,193,194,150,195],"writing","scientific","scientific writing","Citations","deep","deep research","never","papers","journal","false","api","prisma","structure","openrouter","Outlines","core skill","read","features",{"skillNo":197,"name":198,"nameZh":6,"description":199,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":200,"categories":201,"keywords":206,"publishedAt":47},"01M7166ZPKXBF4EBPHVTJPQBB1","scientific-visualization","Meta-skill for publication-ready figures. Use when creating journal submission figures requiring multi-panel layouts, significance annotations, error bars, colorblind-safe palettes, and specific journal formatting (Nature, Science, Cell). Orchestrates matplotlib\u002Fseaborn\u002Fplotly with publication styles. For quick exploration use seaborn or plotly directly.","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fscientific-agent-skills\u002Fskills\u002Fscientific-visualization\u002FSKILL.md",[202,205],{"categoryNo":203,"categoryName":204,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000013","分析与可视化",{"categoryNo":113,"categoryName":114,"taxonomyType":21,"taxonomyTypeDesc":22},[207,179,208,209,210,211,212,213,214,186,32,215,216,217,218,219,220,221,152,222],"visualization","scientific visualization","error","ready","quick","exploration","meta-skill","Meta","safe","plotly","annotations","formatting","Publication","figures","panel","submission",{"skillNo":224,"name":225,"nameZh":6,"description":226,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":227,"categories":228,"keywords":235,"publishedAt":47},"01M7166VXJWQSSC3RQZP60WBGR","research-code","Debug, profile, review, and restructure Python research and analysis code. Use when analysis scripts crash, produce wrong results, run too slowly, or need a correctness review. Covers: reading tracebacks and diagnosing root causes, hypothesis-driven debugging, reviewing code for common statistical\u002Fnumerical errors, profiling data pipelines, improving reproducibility (seeds, environments, determinism), and structuring analysis scripts for sharing. Distinct from \u002Fexploratory-data-analysis (which understands data) and \u002Fstatistical-analysis (which chooses and runs tests) — this skill focuses on the code itself.","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fscientific-agent-skills\u002Fskills\u002Fresearch-code\u002FSKILL.md",[229,232],{"categoryNo":230,"categoryName":231,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":233,"categoryName":234,"taxonomyType":175,"taxonomyTypeDesc":176},"01JBSEEDCAT000000000000030","开发工程师",[236,237,157,238,239,240,241,123,242,32,124,126,243,244,245,246,247,248,194,249],"code","research code","which","memory","data-analysis","errors","debugging","common","review","data pipelines","run","scripts","line","write",{"skillNo":251,"name":252,"nameZh":6,"description":253,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":254,"licenseFileUrl":6,"sourceHtmlUrl":255,"categories":256,"keywords":263,"publishedAt":47},"01M7166CF5HSR7SVZYZFWTDX55","markdown-mermaid-writing","Comprehensive markdown and Mermaid diagram writing skill. Use when creating any scientific document, report, analysis, or visualization. Establishes text-based diagrams as the default documentation standard with full style guides (markdown + mermaid), 24 diagram type references, and 9 document templates.","Apache-2.0","https:\u002F\u002Fgithub.com\u002Ffadrienne\u002FMyGitHub\u002Fblob\u002Fmain\u002Fscientific-agent-skills\u002Fskills\u002Fmarkdown-mermaid-writing\u002FSKILL.md",[257,260,261,262],{"categoryNo":258,"categoryName":259,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000002","文档处理",{"categoryNo":169,"categoryName":170,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":113,"categoryName":114,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":173,"categoryName":174,"taxonomyType":175,"taxonomyTypeDesc":176},[178,264,265,266,267,268,207,269,270,32,124,126,271,272,273,274,275,276,179,194],"markdown mermaid writing","mermaid","markdown","community","diagrams","project","default","team","guides","text","documentation","references","diagram"]