{"adoption": {"forks": 458, "observed_at": "2026-08-28T04:07:57.872852+00:00", "stars": 3354}, "canonical_url": "https://ross.abutalabs.com/products/human-eval", "card": {"archived": false, "artifact_type": "dataset", "description": "Code for the paper \"Evaluating Large Language Models Trained on Code\"", "domain": ["large-language-models", "machine-learning", "developer-tools", "programming-languages"], "enriched": true, "function": ["testing", "benchmarking"], "health_score": 21, "homepage": null, "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["openai/human-eval"], "name": "openai/human-eval", "platform": ["python", "cli", "cross-platform"], "pushed_at": "2025-01-17T18:22:17+00:00", "repo": "openai/human-eval", "stars": 3354, "tags": ["code-generation", "llm-evaluation", "humaneval", "pass-at-k", "benchmark-harness", "unit-tests", "evaluation"], "topics": [], "urls": [], "use_cases": ["benchmark a code-generation LLM on HumanEval", "compute pass@1 pass@10 pass@100 for code completions", "evaluate functional correctness of generated Python code", "compare code models against a standard coding benchmark", "run unit tests against model-generated completions"], "what_it_is": "HumanEval is a hand-written evaluation dataset of 164 Python programming problems with unit tests, plus a harness for measuring code-generation model performance via pass@k functional correctness. It accompanies OpenAI's paper 'Evaluating Large Language Models Trained on Code'.", "when_to_avoid": ["you need a sandboxed execution environment - the harness runs untrusted generated code and deliberately leaves sandboxing to you", "you need evaluation in languages other than Python", "you need a maintained multi-task benchmark suite - this is a single frozen dataset"], "when_to_choose": ["you need a standard, widely-cited benchmark for code generation models", "you want functional-correctness scoring with unit tests rather than string matching", "you are reproducing results from code LLM papers"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/human-eval", "repo": "openai/human-eval", "role": "main", "score": 33}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:07:57.872852+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T18:40:56.279527+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "607df246295104b79b3a2e78368896f53aabf068d9d1e51d4b59aaa82d48ad3e", "fetched_at": "2026-08-28T04:07:57.872852+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/human-eval"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:07:57.872852+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T18:40:56.279527+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "607df246295104b79b3a2e78368896f53aabf068d9d1e51d4b59aaa82d48ad3e", "fetched_at": "2026-08-28T04:07:57.872852+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/human-eval"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T18:40:56.279527+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "607df246295104b79b3a2e78368896f53aabf068d9d1e51d4b59aaa82d48ad3e", "fetched_at": "2026-08-28T04:07:57.872852+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/human-eval"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:07:57.872852+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:07:57.872852+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:07:57.872852+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T18:40:56.279527+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "607df246295104b79b3a2e78368896f53aabf068d9d1e51d4b59aaa82d48ad3e", "fetched_at": "2026-08-28T04:07:57.872852+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/human-eval"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:07:57.872852+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:07:57.872852+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T18:40:56.279527+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "607df246295104b79b3a2e78368896f53aabf068d9d1e51d4b59aaa82d48ad3e", "fetched_at": "2026-08-28T04:07:57.872852+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/human-eval"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:07:57.872852+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:07:57.872852+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:07:57.872852+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T18:40:56.279527+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "607df246295104b79b3a2e78368896f53aabf068d9d1e51d4b59aaa82d48ad3e", "fetched_at": "2026-08-28T04:07:57.872852+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/human-eval"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:07:57.872852+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:07:57.872852+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T18:40:56.279527+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "607df246295104b79b3a2e78368896f53aabf068d9d1e51d4b59aaa82d48ad3e", "fetched_at": "2026-08-28T04:07:57.872852+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/human-eval"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T18:40:56.279527+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "607df246295104b79b3a2e78368896f53aabf068d9d1e51d4b59aaa82d48ad3e", "fetched_at": "2026-08-28T04:07:57.872852+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/human-eval"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T18:40:56.279527+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "607df246295104b79b3a2e78368896f53aabf068d9d1e51d4b59aaa82d48ad3e", "fetched_at": "2026-08-28T04:07:57.872852+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/human-eval"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T18:40:56.279527+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "607df246295104b79b3a2e78368896f53aabf068d9d1e51d4b59aaa82d48ad3e", "fetched_at": "2026-08-28T04:07:57.872852+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/human-eval"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 2, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1884, "days_push": 593, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 33, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}