{"adoption": {"forks": 953, "observed_at": "2026-08-28T04:09:28.240988+00:00", "stars": 5719}, "canonical_url": "https://ross.abutalabs.com/products/swe-bench", "card": {"archived": false, "artifact_type": "dataset", "description": "SWE-bench: Can Language Models Resolve Real-world Github Issues?", "domain": ["large-language-models", "developer-tools", "machine-learning", "testing"], "enriched": true, "function": ["benchmarking", "testing", "machine-learning", "llm-inference", "agent-framework"], "health_score": 79, "homepage": "https://www.swebench.com", "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["SWE-bench/SWE-bench"], "name": "SWE-bench/SWE-bench", "platform": ["python"], "pushed_at": "2026-08-18T23:53:40+00:00", "repo": "SWE-bench/SWE-bench", "stars": 5719, "tags": ["llm-benchmark", "code-generation", "github-issues", "evaluation-harness", "leaderboard", "swe-agent", "patch-generation", "software-engineering", "docker", "linux", "macos"], "topics": ["benchmark", "language-model", "software-engineering"], "urls": [], "use_cases": ["evaluate llm on real github issues", "benchmark coding agents on software engineering tasks", "measure how well a model generates bug-fix patches", "compare coding assistants on a public leaderboard", "run reproducible docker-based code evaluations", "find a dataset of real software engineering problems for llm research"], "what_it_is": "SWE-bench is a benchmark and evaluation harness that tests whether large language models can resolve real-world GitHub issues by generating patches against actual codebases. It ships datasets (SWE-bench, Lite, Verified, Multimodal), a Docker-based reproducible evaluation harness, and official leaderboards.", "when_to_avoid": ["you need a general coding benchmark for simple algorithmic problems (e.g., HumanEval-style)", "you cannot run Docker or containerized evaluations", "you want a lightweight unit-testing framework rather than an LLM evaluation suite"], "when_to_choose": ["you need a standardized, reproducible benchmark for LLM software-engineering ability", "you want to compare your model or agent against published state-of-the-art results", "you need real-world issue/patch data rather than synthetic coding tasks"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/swe-bench", "repo": "SWE-bench/SWE-bench", "role": "main", "score": 72}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:09:28.240988+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T17:53:28.226782+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e964a7f0420c21fe9d78df7806465326244491979f90927fb387634bccc663de", "fetched_at": "2026-08-28T04:09:28.240988+00:00", "kind": "readme", "missing": false, "url": "https://github.com/SWE-bench/SWE-bench"}, {"content_hash": "cf38b8bc341e76557d98611544f058f11450f900e7dbb950a2faa3f9df0a5936", "fetched_at": "2026-08-29T08:49:00.051563+00:00", "kind": "homepage", "missing": false, "url": "https://www.swebench.com"}, {"content_hash": "93ad0eb83f447a177cc7021d483e87d71ee03454f0f2653b66d9d8c3f501d138", "fetched_at": "2026-08-29T08:49:00.060749+00:00", "kind": "site_page", "missing": false, "url": "https://swebench.com/SWE-bench"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:09:28.240988+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T17:53:28.226782+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e964a7f0420c21fe9d78df7806465326244491979f90927fb387634bccc663de", "fetched_at": "2026-08-28T04:09:28.240988+00:00", "kind": "readme", "missing": false, "url": "https://github.com/SWE-bench/SWE-bench"}, {"content_hash": "cf38b8bc341e76557d98611544f058f11450f900e7dbb950a2faa3f9df0a5936", "fetched_at": "2026-08-29T08:49:00.051563+00:00", "kind": "homepage", "missing": false, "url": "https://www.swebench.com"}, {"content_hash": "93ad0eb83f447a177cc7021d483e87d71ee03454f0f2653b66d9d8c3f501d138", "fetched_at": "2026-08-29T08:49:00.060749+00:00", "kind": "site_page", "missing": false, "url": "https://swebench.com/SWE-bench"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T17:53:28.226782+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e964a7f0420c21fe9d78df7806465326244491979f90927fb387634bccc663de", "fetched_at": "2026-08-28T04:09:28.240988+00:00", "kind": "readme", "missing": false, "url": "https://github.com/SWE-bench/SWE-bench"}, {"content_hash": "cf38b8bc341e76557d98611544f058f11450f900e7dbb950a2faa3f9df0a5936", "fetched_at": "2026-08-29T08:49:00.051563+00:00", "kind": "homepage", "missing": false, "url": "https://www.swebench.com"}, {"content_hash": "93ad0eb83f447a177cc7021d483e87d71ee03454f0f2653b66d9d8c3f501d138", "fetched_at": "2026-08-29T08:49:00.060749+00:00", "kind": "site_page", "missing": false, "url": "https://swebench.com/SWE-bench"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:09:28.240988+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:09:28.240988+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:09:28.240988+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T17:53:28.226782+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e964a7f0420c21fe9d78df7806465326244491979f90927fb387634bccc663de", "fetched_at": "2026-08-28T04:09:28.240988+00:00", "kind": "readme", "missing": false, "url": "https://github.com/SWE-bench/SWE-bench"}, {"content_hash": "cf38b8bc341e76557d98611544f058f11450f900e7dbb950a2faa3f9df0a5936", "fetched_at": "2026-08-29T08:49:00.051563+00:00", "kind": "homepage", "missing": false, "url": "https://www.swebench.com"}, {"content_hash": "93ad0eb83f447a177cc7021d483e87d71ee03454f0f2653b66d9d8c3f501d138", "fetched_at": "2026-08-29T08:49:00.060749+00:00", "kind": "site_page", "missing": false, "url": "https://swebench.com/SWE-bench"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:09:28.240988+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:09:28.240988+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T17:53:28.226782+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e964a7f0420c21fe9d78df7806465326244491979f90927fb387634bccc663de", "fetched_at": "2026-08-28T04:09:28.240988+00:00", "kind": "readme", "missing": false, "url": "https://github.com/SWE-bench/SWE-bench"}, {"content_hash": "cf38b8bc341e76557d98611544f058f11450f900e7dbb950a2faa3f9df0a5936", "fetched_at": "2026-08-29T08:49:00.051563+00:00", "kind": "homepage", "missing": false, "url": "https://www.swebench.com"}, {"content_hash": "93ad0eb83f447a177cc7021d483e87d71ee03454f0f2653b66d9d8c3f501d138", "fetched_at": "2026-08-29T08:49:00.060749+00:00", "kind": "site_page", "missing": false, "url": "https://swebench.com/SWE-bench"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:09:28.240988+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:09:28.240988+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:09:28.240988+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T17:53:28.226782+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e964a7f0420c21fe9d78df7806465326244491979f90927fb387634bccc663de", "fetched_at": "2026-08-28T04:09:28.240988+00:00", "kind": "readme", "missing": false, "url": "https://github.com/SWE-bench/SWE-bench"}, {"content_hash": "cf38b8bc341e76557d98611544f058f11450f900e7dbb950a2faa3f9df0a5936", "fetched_at": "2026-08-29T08:49:00.051563+00:00", "kind": "homepage", "missing": false, "url": "https://www.swebench.com"}, {"content_hash": "93ad0eb83f447a177cc7021d483e87d71ee03454f0f2653b66d9d8c3f501d138", "fetched_at": "2026-08-29T08:49:00.060749+00:00", "kind": "site_page", "missing": false, "url": "https://swebench.com/SWE-bench"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:09:28.240988+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:09:28.240988+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T17:53:28.226782+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e964a7f0420c21fe9d78df7806465326244491979f90927fb387634bccc663de", "fetched_at": "2026-08-28T04:09:28.240988+00:00", "kind": "readme", "missing": false, "url": "https://github.com/SWE-bench/SWE-bench"}, {"content_hash": "cf38b8bc341e76557d98611544f058f11450f900e7dbb950a2faa3f9df0a5936", "fetched_at": "2026-08-29T08:49:00.051563+00:00", "kind": "homepage", "missing": false, "url": "https://www.swebench.com"}, {"content_hash": "93ad0eb83f447a177cc7021d483e87d71ee03454f0f2653b66d9d8c3f501d138", "fetched_at": "2026-08-29T08:49:00.060749+00:00", "kind": "site_page", "missing": false, "url": "https://swebench.com/SWE-bench"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T17:53:28.226782+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e964a7f0420c21fe9d78df7806465326244491979f90927fb387634bccc663de", "fetched_at": "2026-08-28T04:09:28.240988+00:00", "kind": "readme", "missing": false, "url": "https://github.com/SWE-bench/SWE-bench"}, {"content_hash": "cf38b8bc341e76557d98611544f058f11450f900e7dbb950a2faa3f9df0a5936", "fetched_at": "2026-08-29T08:49:00.051563+00:00", "kind": "homepage", "missing": false, "url": "https://www.swebench.com"}, {"content_hash": "93ad0eb83f447a177cc7021d483e87d71ee03454f0f2653b66d9d8c3f501d138", "fetched_at": "2026-08-29T08:49:00.060749+00:00", "kind": "site_page", "missing": false, "url": "https://swebench.com/SWE-bench"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T17:53:28.226782+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e964a7f0420c21fe9d78df7806465326244491979f90927fb387634bccc663de", "fetched_at": "2026-08-28T04:09:28.240988+00:00", "kind": "readme", "missing": false, "url": "https://github.com/SWE-bench/SWE-bench"}, {"content_hash": "cf38b8bc341e76557d98611544f058f11450f900e7dbb950a2faa3f9df0a5936", "fetched_at": "2026-08-29T08:49:00.051563+00:00", "kind": "homepage", "missing": false, "url": "https://www.swebench.com"}, {"content_hash": "93ad0eb83f447a177cc7021d483e87d71ee03454f0f2653b66d9d8c3f501d138", "fetched_at": "2026-08-29T08:49:00.060749+00:00", "kind": "site_page", "missing": false, "url": "https://swebench.com/SWE-bench"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T17:53:28.226782+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e964a7f0420c21fe9d78df7806465326244491979f90927fb387634bccc663de", "fetched_at": "2026-08-28T04:09:28.240988+00:00", "kind": "readme", "missing": false, "url": "https://github.com/SWE-bench/SWE-bench"}, {"content_hash": "cf38b8bc341e76557d98611544f058f11450f900e7dbb950a2faa3f9df0a5936", "fetched_at": "2026-08-29T08:49:00.051563+00:00", "kind": "homepage", "missing": false, "url": "https://www.swebench.com"}, {"content_hash": "93ad0eb83f447a177cc7021d483e87d71ee03454f0f2653b66d9d8c3f501d138", "fetched_at": "2026-08-29T08:49:00.060749+00:00", "kind": "site_page", "missing": false, "url": "https://swebench.com/SWE-bench"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 98, "longevity": 76, "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": 1065, "days_push": 15, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 72, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}