{"adoption": {"forks": 119, "observed_at": "2026-08-28T04:04:16.349389+00:00", "stars": 1294}, "canonical_url": "https://ross.abutalabs.com/products/livebench", "card": {"archived": false, "artifact_type": "dataset", "description": "LiveBench: A Challenging, Contamination-Free LLM Benchmark", "domain": ["large-language-models", "machine-learning", "artificial-intelligence"], "enriched": true, "function": ["benchmarking", "llm-inference", "testing"], "health_score": 80, "homepage": null, "language": "Python", "license": "NOASSERTION", "license_family": "other", "maturity": "active", "member_repos": ["LiveBench/LiveBench"], "name": "LiveBench/LiveBench", "platform": ["python", "cli"], "pushed_at": "2026-08-26T15:00:50+00:00", "repo": "LiveBench/LiveBench", "stars": 1294, "tags": ["llm-benchmark", "contamination-free", "evaluation", "leaderboard", "model-evaluation", "docker"], "topics": [], "urls": [], "use_cases": ["benchmark llm performance without test set contamination", "evaluate my model on a public leaderboard", "score llm answers objectively without an llm judge", "run monthly fresh benchmark questions for chat models", "compare api models on coding math and instruction following tasks", "evaluate agentic coding questions in docker"], "what_it_is": "LiveBench is a contamination-free benchmark for large language models that releases new questions monthly, drawn from recent datasets, papers, news, and IMDb synopses. It includes 18 diverse tasks across 6 categories with objective, verifiable ground-truth answers that are scored automatically without an LLM judge.", "when_to_avoid": ["you need local model inference support, which is unmaintained", "you need a static benchmark with a fixed question set", "you need subjective or open-ended evaluation criteria"], "when_to_choose": ["you need contamination-resistant evaluation of LLMs", "you want automatic objective scoring without judge models", "you want to submit a model to a public leaderboard"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/livebench", "repo": "LiveBench/LiveBench", "role": "main", "score": 68}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:16.349389+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:54:03.277043+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "eb1d2aa733471b95620d5914d45abf4379f7e370e438f0b870d21b6acf2c86a9", "fetched_at": "2026-08-28T04:04:16.349389+00:00", "kind": "readme", "missing": false, "url": "https://github.com/LiveBench/LiveBench"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:16.349389+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:54:03.277043+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "eb1d2aa733471b95620d5914d45abf4379f7e370e438f0b870d21b6acf2c86a9", "fetched_at": "2026-08-28T04:04:16.349389+00:00", "kind": "readme", "missing": false, "url": "https://github.com/LiveBench/LiveBench"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:54:03.277043+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "eb1d2aa733471b95620d5914d45abf4379f7e370e438f0b870d21b6acf2c86a9", "fetched_at": "2026-08-28T04:04:16.349389+00:00", "kind": "readme", "missing": false, "url": "https://github.com/LiveBench/LiveBench"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:16.349389+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:16.349389+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:16.349389+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:54:03.277043+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "eb1d2aa733471b95620d5914d45abf4379f7e370e438f0b870d21b6acf2c86a9", "fetched_at": "2026-08-28T04:04:16.349389+00:00", "kind": "readme", "missing": false, "url": "https://github.com/LiveBench/LiveBench"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:16.349389+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:16.349389+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:54:03.277043+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "eb1d2aa733471b95620d5914d45abf4379f7e370e438f0b870d21b6acf2c86a9", "fetched_at": "2026-08-28T04:04:16.349389+00:00", "kind": "readme", "missing": false, "url": "https://github.com/LiveBench/LiveBench"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:16.349389+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:16.349389+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:16.349389+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:54:03.277043+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "eb1d2aa733471b95620d5914d45abf4379f7e370e438f0b870d21b6acf2c86a9", "fetched_at": "2026-08-28T04:04:16.349389+00:00", "kind": "readme", "missing": false, "url": "https://github.com/LiveBench/LiveBench"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:16.349389+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:16.349389+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:54:03.277043+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "eb1d2aa733471b95620d5914d45abf4379f7e370e438f0b870d21b6acf2c86a9", "fetched_at": "2026-08-28T04:04:16.349389+00:00", "kind": "readme", "missing": false, "url": "https://github.com/LiveBench/LiveBench"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:54:03.277043+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "eb1d2aa733471b95620d5914d45abf4379f7e370e438f0b870d21b6acf2c86a9", "fetched_at": "2026-08-28T04:04:16.349389+00:00", "kind": "readme", "missing": false, "url": "https://github.com/LiveBench/LiveBench"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:54:03.277043+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "eb1d2aa733471b95620d5914d45abf4379f7e370e438f0b870d21b6acf2c86a9", "fetched_at": "2026-08-28T04:04:16.349389+00:00", "kind": "readme", "missing": false, "url": "https://github.com/LiveBench/LiveBench"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:54:03.277043+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "eb1d2aa733471b95620d5914d45abf4379f7e370e438f0b870d21b6acf2c86a9", "fetched_at": "2026-08-28T04:04:16.349389+00:00", "kind": "readme", "missing": false, "url": "https://github.com/LiveBench/LiveBench"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 99, "longevity": 58, "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": 812, "days_push": 7, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 68, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}