{"adoption": {"forks": 192, "observed_at": "2026-08-28T04:04:00.798616+00:00", "stars": 1214}, "canonical_url": "https://ross.abutalabs.com/products/kernelbench", "card": {"archived": false, "artifact_type": "dataset", "description": "KernelBench: Can LLMs Write GPU Kernels? - Benchmark + Toolkit with Torch -> CUDA (+ more DSLs)", "domain": ["large-language-models", "machine-learning", "gpu-computing", "developer-tools", "artificial-intelligence"], "enriched": true, "function": ["benchmarking", "llm-training", "machine-learning", "gpu-computing"], "health_score": 64, "homepage": "https://scalingintelligence.stanford.edu/blogs/kernelbench/", "language": "Jupyter Notebook", "license": "NOASSERTION", "license_family": "other", "maturity": "active", "member_repos": ["ScalingIntelligence/KernelBench"], "name": "ScalingIntelligence/KernelBench", "platform": ["python", "cli"], "pushed_at": "2026-03-24T04:29:13+00:00", "repo": "ScalingIntelligence/KernelBench", "stars": 1214, "tags": ["llm-benchmark", "cuda-codegen", "kernel-generation", "code-evaluation", "rl-environment", "pytorch", "evaluation", "gpu", "linux"], "topics": ["benchmark", "codegen", "evaluation", "gpu", "tooling", "rl-environment"], "urls": [], "use_cases": ["benchmark llm code generation for cuda kernels", "evaluate if a model can write efficient gpu kernels", "measure speedup of llm-generated kernels against pytorch baselines", "use kernel optimization tasks as an rl environment for training models", "compare codegen models on gpu kernel transpilation", "optimize pytorch operators with custom cuda kernels"], "what_it_is": "KernelBench is a benchmark and toolkit from Stanford's Scaling Intelligence Lab that evaluates whether LLMs can generate correct and efficient GPU kernels from PyTorch programs. It provides 250+ tasks across four difficulty levels, evaluation scripts for correctness and speedup checks, and a HuggingFace dataset.", "when_to_avoid": ["you need a production tool to auto-generate kernels for your app", "you have no gpu hardware available", "you want a turnkey agentic scaffold rather than a benchmark toolkit"], "when_to_choose": ["you need a standardized benchmark for llm gpu kernel generation", "you want to evaluate or train models on cuda code generation tasks", "you are researching agentic kernel optimization with profiling feedback"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/kernelbench", "repo": "ScalingIntelligence/KernelBench", "role": "main", "score": 55}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:00.798616+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:17:20.510300+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b64c5ac676fb58cf0bef79a828f46c143017c8618b3f8a9366989d102089d359", "fetched_at": "2026-08-28T04:04:00.798616+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ScalingIntelligence/KernelBench"}, {"content_hash": "694d214d031c3e4fdfe3e73843ba0196254804cd90fa0adbbf64407c139b1cb8", "fetched_at": "2026-08-29T12:25:31.981956+00:00", "kind": "homepage", "missing": false, "url": "https://scalingintelligence.stanford.edu/blogs/kernelbench/"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:00.798616+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:17:20.510300+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b64c5ac676fb58cf0bef79a828f46c143017c8618b3f8a9366989d102089d359", "fetched_at": "2026-08-28T04:04:00.798616+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ScalingIntelligence/KernelBench"}, {"content_hash": "694d214d031c3e4fdfe3e73843ba0196254804cd90fa0adbbf64407c139b1cb8", "fetched_at": "2026-08-29T12:25:31.981956+00:00", "kind": "homepage", "missing": false, "url": "https://scalingintelligence.stanford.edu/blogs/kernelbench/"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:17:20.510300+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b64c5ac676fb58cf0bef79a828f46c143017c8618b3f8a9366989d102089d359", "fetched_at": "2026-08-28T04:04:00.798616+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ScalingIntelligence/KernelBench"}, {"content_hash": "694d214d031c3e4fdfe3e73843ba0196254804cd90fa0adbbf64407c139b1cb8", "fetched_at": "2026-08-29T12:25:31.981956+00:00", "kind": "homepage", "missing": false, "url": "https://scalingintelligence.stanford.edu/blogs/kernelbench/"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:00.798616+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:00.798616+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:00.798616+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:17:20.510300+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b64c5ac676fb58cf0bef79a828f46c143017c8618b3f8a9366989d102089d359", "fetched_at": "2026-08-28T04:04:00.798616+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ScalingIntelligence/KernelBench"}, {"content_hash": "694d214d031c3e4fdfe3e73843ba0196254804cd90fa0adbbf64407c139b1cb8", "fetched_at": "2026-08-29T12:25:31.981956+00:00", "kind": "homepage", "missing": false, "url": "https://scalingintelligence.stanford.edu/blogs/kernelbench/"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:00.798616+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:00.798616+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:17:20.510300+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b64c5ac676fb58cf0bef79a828f46c143017c8618b3f8a9366989d102089d359", "fetched_at": "2026-08-28T04:04:00.798616+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ScalingIntelligence/KernelBench"}, {"content_hash": "694d214d031c3e4fdfe3e73843ba0196254804cd90fa0adbbf64407c139b1cb8", "fetched_at": "2026-08-29T12:25:31.981956+00:00", "kind": "homepage", "missing": false, "url": "https://scalingintelligence.stanford.edu/blogs/kernelbench/"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:00.798616+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:00.798616+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:00.798616+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:17:20.510300+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b64c5ac676fb58cf0bef79a828f46c143017c8618b3f8a9366989d102089d359", "fetched_at": "2026-08-28T04:04:00.798616+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ScalingIntelligence/KernelBench"}, {"content_hash": "694d214d031c3e4fdfe3e73843ba0196254804cd90fa0adbbf64407c139b1cb8", "fetched_at": "2026-08-29T12:25:31.981956+00:00", "kind": "homepage", "missing": false, "url": "https://scalingintelligence.stanford.edu/blogs/kernelbench/"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:00.798616+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:00.798616+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:17:20.510300+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b64c5ac676fb58cf0bef79a828f46c143017c8618b3f8a9366989d102089d359", "fetched_at": "2026-08-28T04:04:00.798616+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ScalingIntelligence/KernelBench"}, {"content_hash": "694d214d031c3e4fdfe3e73843ba0196254804cd90fa0adbbf64407c139b1cb8", "fetched_at": "2026-08-29T12:25:31.981956+00:00", "kind": "homepage", "missing": false, "url": "https://scalingintelligence.stanford.edu/blogs/kernelbench/"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:17:20.510300+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b64c5ac676fb58cf0bef79a828f46c143017c8618b3f8a9366989d102089d359", "fetched_at": "2026-08-28T04:04:00.798616+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ScalingIntelligence/KernelBench"}, {"content_hash": "694d214d031c3e4fdfe3e73843ba0196254804cd90fa0adbbf64407c139b1cb8", "fetched_at": "2026-08-29T12:25:31.981956+00:00", "kind": "homepage", "missing": false, "url": "https://scalingintelligence.stanford.edu/blogs/kernelbench/"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:17:20.510300+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b64c5ac676fb58cf0bef79a828f46c143017c8618b3f8a9366989d102089d359", "fetched_at": "2026-08-28T04:04:00.798616+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ScalingIntelligence/KernelBench"}, {"content_hash": "694d214d031c3e4fdfe3e73843ba0196254804cd90fa0adbbf64407c139b1cb8", "fetched_at": "2026-08-29T12:25:31.981956+00:00", "kind": "homepage", "missing": false, "url": "https://scalingintelligence.stanford.edu/blogs/kernelbench/"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:17:20.510300+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b64c5ac676fb58cf0bef79a828f46c143017c8618b3f8a9366989d102089d359", "fetched_at": "2026-08-28T04:04:00.798616+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ScalingIntelligence/KernelBench"}, {"content_hash": "694d214d031c3e4fdfe3e73843ba0196254804cd90fa0adbbf64407c139b1cb8", "fetched_at": "2026-08-29T12:25:31.981956+00:00", "kind": "homepage", "missing": false, "url": "https://scalingintelligence.stanford.edu/blogs/kernelbench/"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 73, "longevity": 48, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases", "no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 678, "days_push": 162, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 55, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}