{"adoption": {"forks": 257, "observed_at": "2026-08-28T04:05:26.610836+00:00", "stars": 1720}, "canonical_url": "https://ross.abutalabs.com/products/mle-bench", "card": {"archived": false, "artifact_type": "dataset", "description": "MLE-bench is a benchmark for measuring how well AI agents perform at machine learning engineering", "domain": ["machine-learning", "artificial-intelligence", "developer-tools", "tutorials"], "enriched": true, "function": ["benchmarking", "agent-framework", "machine-learning", "testing"], "health_score": 67, "homepage": "https://openai.com/index/mle-bench/", "language": "Python", "license": "NOASSERTION", "license_family": "other", "maturity": "active", "member_repos": ["openai/mle-bench"], "name": "openai/mle-bench", "platform": ["python", "cross-platform"], "pushed_at": "2026-04-24T17:33:44+00:00", "repo": "openai/mle-bench", "stars": 1720, "tags": ["kaggle", "evaluation", "llm-agents", "ml-engineering", "leaderboard", "openai", "ai-agents", "docker", "linux"], "topics": [], "urls": [], "use_cases": ["evaluate how well an LLM agent does machine learning engineering", "benchmark AI agents on Kaggle-style ML competitions", "compare agent scaffolds like AIDE on ML tasks", "measure whether an agent can train models and prepare datasets autonomously", "research contamination and resource scaling for ML agents", "reproduce the MLE-bench leaderboard results for a new agent"], "what_it_is": "MLE-bench is an open-source benchmark from OpenAI that measures how well AI agents perform machine learning engineering tasks, built from 75 Kaggle competitions with human baselines. It includes dataset construction code, evaluation/grading logic, and agent scaffolds for evaluating frontier LLMs.", "when_to_avoid": ["you need a general coding benchmark like SWE-bench rather than ML-specific tasks", "you want a production tool for running ML pipelines rather than an evaluation benchmark", "you require an actively accepting leaderboard submissions (currently paused)"], "when_to_choose": ["you are researching or benchmarking LLM agents on real-world ML engineering tasks", "you want standardized Kaggle-derived tasks with human baselines and grading", "you need open-source evaluation harness code and reference agent scaffolds"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/mle-bench", "repo": "openai/mle-bench", "role": "main", "score": 58}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:26.610836+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:34:05.422167+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f75375122f4c0496708c2ba21b6e84d06c6642e2ae47d4e53b8b12689a0b0362", "fetched_at": "2026-08-28T04:05:26.610836+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/mle-bench"}, {"content_hash": "688b58243c42ddcf62d067b50142d3bf322e9d40e36249b8d8c10c146bfbd9cb", "fetched_at": "2026-08-29T11:09:57.388798+00:00", "kind": "homepage", "missing": false, "url": "https://openai.com/index/mle-bench/"}, {"content_hash": "de4b627b33e34c6378d078a5da3cbfcc942df598db166981f7cd976535c0a501", "fetched_at": "2026-08-29T11:09:57.398570+00:00", "kind": "site_page", "missing": false, "url": "https://openai.com/about"}, {"content_hash": "d617c5215f2a3c25137a2ffb371a818fc9c246fffe03713dcd7b757690335d76", "fetched_at": "2026-08-29T11:09:57.400826+00:00", "kind": "site_page", "missing": false, "url": "https://developers.openai.com/api/docs"}, {"content_hash": "7d240c906018bf9c33351c36a70813e1afb8403553ceaca27c8029f0e671e3a7", "fetched_at": "2026-08-29T11:09:57.403130+00:00", "kind": "site_page", "missing": false, "url": "https://developers.openai.com/"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:26.610836+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:34:05.422167+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f75375122f4c0496708c2ba21b6e84d06c6642e2ae47d4e53b8b12689a0b0362", "fetched_at": "2026-08-28T04:05:26.610836+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/mle-bench"}, {"content_hash": "688b58243c42ddcf62d067b50142d3bf322e9d40e36249b8d8c10c146bfbd9cb", "fetched_at": "2026-08-29T11:09:57.388798+00:00", "kind": "homepage", "missing": false, "url": "https://openai.com/index/mle-bench/"}, {"content_hash": "de4b627b33e34c6378d078a5da3cbfcc942df598db166981f7cd976535c0a501", "fetched_at": "2026-08-29T11:09:57.398570+00:00", "kind": "site_page", "missing": false, "url": "https://openai.com/about"}, {"content_hash": "d617c5215f2a3c25137a2ffb371a818fc9c246fffe03713dcd7b757690335d76", "fetched_at": "2026-08-29T11:09:57.400826+00:00", "kind": "site_page", "missing": false, "url": "https://developers.openai.com/api/docs"}, {"content_hash": "7d240c906018bf9c33351c36a70813e1afb8403553ceaca27c8029f0e671e3a7", "fetched_at": "2026-08-29T11:09:57.403130+00:00", "kind": "site_page", "missing": false, "url": "https://developers.openai.com/"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:34:05.422167+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f75375122f4c0496708c2ba21b6e84d06c6642e2ae47d4e53b8b12689a0b0362", "fetched_at": "2026-08-28T04:05:26.610836+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/mle-bench"}, {"content_hash": "688b58243c42ddcf62d067b50142d3bf322e9d40e36249b8d8c10c146bfbd9cb", "fetched_at": "2026-08-29T11:09:57.388798+00:00", "kind": "homepage", "missing": false, "url": "https://openai.com/index/mle-bench/"}, {"content_hash": "de4b627b33e34c6378d078a5da3cbfcc942df598db166981f7cd976535c0a501", "fetched_at": "2026-08-29T11:09:57.398570+00:00", "kind": "site_page", "missing": false, "url": "https://openai.com/about"}, {"content_hash": "d617c5215f2a3c25137a2ffb371a818fc9c246fffe03713dcd7b757690335d76", "fetched_at": "2026-08-29T11:09:57.400826+00:00", "kind": "site_page", "missing": false, "url": "https://developers.openai.com/api/docs"}, {"content_hash": "7d240c906018bf9c33351c36a70813e1afb8403553ceaca27c8029f0e671e3a7", "fetched_at": "2026-08-29T11:09:57.403130+00:00", "kind": "site_page", "missing": false, "url": "https://developers.openai.com/"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:26.610836+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:26.610836+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:26.610836+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:34:05.422167+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f75375122f4c0496708c2ba21b6e84d06c6642e2ae47d4e53b8b12689a0b0362", "fetched_at": "2026-08-28T04:05:26.610836+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/mle-bench"}, {"content_hash": "688b58243c42ddcf62d067b50142d3bf322e9d40e36249b8d8c10c146bfbd9cb", "fetched_at": "2026-08-29T11:09:57.388798+00:00", "kind": "homepage", "missing": false, "url": "https://openai.com/index/mle-bench/"}, {"content_hash": "de4b627b33e34c6378d078a5da3cbfcc942df598db166981f7cd976535c0a501", "fetched_at": "2026-08-29T11:09:57.398570+00:00", "kind": "site_page", "missing": false, "url": "https://openai.com/about"}, {"content_hash": "d617c5215f2a3c25137a2ffb371a818fc9c246fffe03713dcd7b757690335d76", "fetched_at": "2026-08-29T11:09:57.400826+00:00", "kind": "site_page", "missing": false, "url": "https://developers.openai.com/api/docs"}, {"content_hash": "7d240c906018bf9c33351c36a70813e1afb8403553ceaca27c8029f0e671e3a7", "fetched_at": "2026-08-29T11:09:57.403130+00:00", "kind": "site_page", "missing": false, "url": "https://developers.openai.com/"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:26.610836+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:26.610836+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:34:05.422167+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f75375122f4c0496708c2ba21b6e84d06c6642e2ae47d4e53b8b12689a0b0362", "fetched_at": "2026-08-28T04:05:26.610836+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/mle-bench"}, {"content_hash": "688b58243c42ddcf62d067b50142d3bf322e9d40e36249b8d8c10c146bfbd9cb", "fetched_at": "2026-08-29T11:09:57.388798+00:00", "kind": "homepage", "missing": false, "url": "https://openai.com/index/mle-bench/"}, {"content_hash": "de4b627b33e34c6378d078a5da3cbfcc942df598db166981f7cd976535c0a501", "fetched_at": "2026-08-29T11:09:57.398570+00:00", "kind": "site_page", "missing": false, "url": "https://openai.com/about"}, {"content_hash": "d617c5215f2a3c25137a2ffb371a818fc9c246fffe03713dcd7b757690335d76", "fetched_at": "2026-08-29T11:09:57.400826+00:00", "kind": "site_page", "missing": false, "url": "https://developers.openai.com/api/docs"}, {"content_hash": "7d240c906018bf9c33351c36a70813e1afb8403553ceaca27c8029f0e671e3a7", "fetched_at": "2026-08-29T11:09:57.403130+00:00", "kind": "site_page", "missing": false, "url": "https://developers.openai.com/"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:26.610836+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:26.610836+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:26.610836+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:34:05.422167+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f75375122f4c0496708c2ba21b6e84d06c6642e2ae47d4e53b8b12689a0b0362", "fetched_at": "2026-08-28T04:05:26.610836+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/mle-bench"}, {"content_hash": "688b58243c42ddcf62d067b50142d3bf322e9d40e36249b8d8c10c146bfbd9cb", "fetched_at": "2026-08-29T11:09:57.388798+00:00", "kind": "homepage", "missing": false, "url": "https://openai.com/index/mle-bench/"}, {"content_hash": "de4b627b33e34c6378d078a5da3cbfcc942df598db166981f7cd976535c0a501", "fetched_at": "2026-08-29T11:09:57.398570+00:00", "kind": "site_page", "missing": false, "url": "https://openai.com/about"}, {"content_hash": "d617c5215f2a3c25137a2ffb371a818fc9c246fffe03713dcd7b757690335d76", "fetched_at": "2026-08-29T11:09:57.400826+00:00", "kind": "site_page", "missing": false, "url": "https://developers.openai.com/api/docs"}, {"content_hash": "7d240c906018bf9c33351c36a70813e1afb8403553ceaca27c8029f0e671e3a7", "fetched_at": "2026-08-29T11:09:57.403130+00:00", "kind": "site_page", "missing": false, "url": "https://developers.openai.com/"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:26.610836+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:26.610836+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:34:05.422167+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f75375122f4c0496708c2ba21b6e84d06c6642e2ae47d4e53b8b12689a0b0362", "fetched_at": "2026-08-28T04:05:26.610836+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/mle-bench"}, {"content_hash": "688b58243c42ddcf62d067b50142d3bf322e9d40e36249b8d8c10c146bfbd9cb", "fetched_at": "2026-08-29T11:09:57.388798+00:00", "kind": "homepage", "missing": false, "url": "https://openai.com/index/mle-bench/"}, {"content_hash": "de4b627b33e34c6378d078a5da3cbfcc942df598db166981f7cd976535c0a501", "fetched_at": "2026-08-29T11:09:57.398570+00:00", "kind": "site_page", "missing": false, "url": "https://openai.com/about"}, {"content_hash": "d617c5215f2a3c25137a2ffb371a818fc9c246fffe03713dcd7b757690335d76", "fetched_at": "2026-08-29T11:09:57.400826+00:00", "kind": "site_page", "missing": false, "url": "https://developers.openai.com/api/docs"}, {"content_hash": "7d240c906018bf9c33351c36a70813e1afb8403553ceaca27c8029f0e671e3a7", "fetched_at": "2026-08-29T11:09:57.403130+00:00", "kind": "site_page", "missing": false, "url": "https://developers.openai.com/"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:34:05.422167+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f75375122f4c0496708c2ba21b6e84d06c6642e2ae47d4e53b8b12689a0b0362", "fetched_at": "2026-08-28T04:05:26.610836+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/mle-bench"}, {"content_hash": "688b58243c42ddcf62d067b50142d3bf322e9d40e36249b8d8c10c146bfbd9cb", "fetched_at": "2026-08-29T11:09:57.388798+00:00", "kind": "homepage", "missing": false, "url": "https://openai.com/index/mle-bench/"}, {"content_hash": "de4b627b33e34c6378d078a5da3cbfcc942df598db166981f7cd976535c0a501", "fetched_at": "2026-08-29T11:09:57.398570+00:00", "kind": "site_page", "missing": false, "url": "https://openai.com/about"}, {"content_hash": "d617c5215f2a3c25137a2ffb371a818fc9c246fffe03713dcd7b757690335d76", "fetched_at": "2026-08-29T11:09:57.400826+00:00", "kind": "site_page", "missing": false, "url": "https://developers.openai.com/api/docs"}, {"content_hash": "7d240c906018bf9c33351c36a70813e1afb8403553ceaca27c8029f0e671e3a7", "fetched_at": "2026-08-29T11:09:57.403130+00:00", "kind": "site_page", "missing": false, "url": "https://developers.openai.com/"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:34:05.422167+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f75375122f4c0496708c2ba21b6e84d06c6642e2ae47d4e53b8b12689a0b0362", "fetched_at": "2026-08-28T04:05:26.610836+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/mle-bench"}, {"content_hash": "688b58243c42ddcf62d067b50142d3bf322e9d40e36249b8d8c10c146bfbd9cb", "fetched_at": "2026-08-29T11:09:57.388798+00:00", "kind": "homepage", "missing": false, "url": "https://openai.com/index/mle-bench/"}, {"content_hash": "de4b627b33e34c6378d078a5da3cbfcc942df598db166981f7cd976535c0a501", "fetched_at": "2026-08-29T11:09:57.398570+00:00", "kind": "site_page", "missing": false, "url": "https://openai.com/about"}, {"content_hash": "d617c5215f2a3c25137a2ffb371a818fc9c246fffe03713dcd7b757690335d76", "fetched_at": "2026-08-29T11:09:57.400826+00:00", "kind": "site_page", "missing": false, "url": "https://developers.openai.com/api/docs"}, {"content_hash": "7d240c906018bf9c33351c36a70813e1afb8403553ceaca27c8029f0e671e3a7", "fetched_at": "2026-08-29T11:09:57.403130+00:00", "kind": "site_page", "missing": false, "url": "https://developers.openai.com/"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:34:05.422167+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "f75375122f4c0496708c2ba21b6e84d06c6642e2ae47d4e53b8b12689a0b0362", "fetched_at": "2026-08-28T04:05:26.610836+00:00", "kind": "readme", "missing": false, "url": "https://github.com/openai/mle-bench"}, {"content_hash": "688b58243c42ddcf62d067b50142d3bf322e9d40e36249b8d8c10c146bfbd9cb", "fetched_at": "2026-08-29T11:09:57.388798+00:00", "kind": "homepage", "missing": false, "url": "https://openai.com/index/mle-bench/"}, {"content_hash": "de4b627b33e34c6378d078a5da3cbfcc942df598db166981f7cd976535c0a501", "fetched_at": "2026-08-29T11:09:57.398570+00:00", "kind": "site_page", "missing": false, "url": "https://openai.com/about"}, {"content_hash": "d617c5215f2a3c25137a2ffb371a818fc9c246fffe03713dcd7b757690335d76", "fetched_at": "2026-08-29T11:09:57.400826+00:00", "kind": "site_page", "missing": false, "url": "https://developers.openai.com/api/docs"}, {"content_hash": "7d240c906018bf9c33351c36a70813e1afb8403553ceaca27c8029f0e671e3a7", "fetched_at": "2026-08-29T11:09:57.403130+00:00", "kind": "site_page", "missing": false, "url": "https://developers.openai.com/"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 79, "longevity": 49, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+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": 694, "days_push": 131, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 58, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}