{"adoption": {"forks": 618, "observed_at": "2026-08-28T04:07:50.691880+00:00", "stars": 3247}, "canonical_url": "https://ross.abutalabs.com/products/big-bench", "card": {"archived": true, "artifact_type": "dataset", "description": "Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models", "domain": ["large-language-models", "machine-learning", "artificial-intelligence", "tutorials"], "enriched": true, "function": ["benchmarking", "machine-learning", "nlp", "llm-inference", "testing"], "health_score": 10, "homepage": null, "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["google/BIG-bench"], "name": "google/BIG-bench", "platform": ["python", "cross-platform"], "pushed_at": "2024-07-19T11:57:37+00:00", "repo": "google/BIG-bench", "stars": 3247, "tags": ["llm-evaluation", "benchmark", "language-models", "evaluation-suite", "leaderboard", "natural-language-processing"], "topics": [], "urls": [], "use_cases": ["evaluate large language models on diverse tasks", "benchmark my LLM against other models", "find tasks that probe LLM reasoning capabilities", "compare language model performance on a leaderboard", "create custom benchmark tasks for language models", "measure how LLM capabilities scale with model size"], "what_it_is": "BIG-bench is a collaborative benchmark with over 200 tasks for probing and measuring the capabilities of large language models. It includes a Python evaluation harness, a lightweight 24-task subset (BIG-bench Lite), and a public leaderboard for comparing model performance.", "when_to_avoid": ["you need a lightweight, fast evaluation of a single narrow capability", "you want a benchmark focused only on the newest frontier models or agentic tasks", "you need production inference tooling rather than evaluation"], "when_to_choose": ["you need a broad, community-accepted suite of tasks to evaluate LLMs", "you want to compare your model against published results on a standard leaderboard", "you are researching how language model capabilities extrapolate with scale"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/big-bench", "repo": "google/BIG-bench", "role": "main", "score": 10}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:07:50.691880+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T07:24:28.179520+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e26b6175749803026c06fe911f76ce4bd7298129e53ea86c504813d91ab3305f", "fetched_at": "2026-08-28T04:07:50.691880+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google/BIG-bench"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:07:50.691880+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T07:24:28.179520+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e26b6175749803026c06fe911f76ce4bd7298129e53ea86c504813d91ab3305f", "fetched_at": "2026-08-28T04:07:50.691880+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google/BIG-bench"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T07:24:28.179520+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e26b6175749803026c06fe911f76ce4bd7298129e53ea86c504813d91ab3305f", "fetched_at": "2026-08-28T04:07:50.691880+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google/BIG-bench"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:07:50.691880+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:07:50.691880+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:07:50.691880+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T07:24:28.179520+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e26b6175749803026c06fe911f76ce4bd7298129e53ea86c504813d91ab3305f", "fetched_at": "2026-08-28T04:07:50.691880+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google/BIG-bench"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:07:50.691880+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:07:50.691880+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T07:24:28.179520+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e26b6175749803026c06fe911f76ce4bd7298129e53ea86c504813d91ab3305f", "fetched_at": "2026-08-28T04:07:50.691880+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google/BIG-bench"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:07:50.691880+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:07:50.691880+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:07:50.691880+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T07:24:28.179520+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e26b6175749803026c06fe911f76ce4bd7298129e53ea86c504813d91ab3305f", "fetched_at": "2026-08-28T04:07:50.691880+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google/BIG-bench"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:07:50.691880+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:07:50.691880+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T07:24:28.179520+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e26b6175749803026c06fe911f76ce4bd7298129e53ea86c504813d91ab3305f", "fetched_at": "2026-08-28T04:07:50.691880+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google/BIG-bench"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T07:24:28.179520+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e26b6175749803026c06fe911f76ce4bd7298129e53ea86c504813d91ab3305f", "fetched_at": "2026-08-28T04:07:50.691880+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google/BIG-bench"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T07:24:28.179520+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e26b6175749803026c06fe911f76ce4bd7298129e53ea86c504813d91ab3305f", "fetched_at": "2026-08-28T04:07:50.691880+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google/BIG-bench"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T07:24:28.179520+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "e26b6175749803026c06fe911f76ce4bd7298129e53ea86c504813d91ab3305f", "fetched_at": "2026-08-28T04:07:50.691880+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google/BIG-bench"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases", "archived"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 2056, "days_push": 775, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 10, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}