{"adoption": {"forks": 315, "observed_at": "2026-08-28T04:06:05.197717+00:00", "stars": 2012}, "canonical_url": "https://ross.abutalabs.com/products/alpaca_eval", "card": {"archived": false, "artifact_type": "library", "description": "An automatic evaluator for instruction-following language models. Human-validated, high-quality, cheap, and fast.", "domain": ["large-language-models", "machine-learning", "developer-tools"], "enriched": true, "function": ["benchmarking", "llm-inference", "machine-learning", "cli"], "health_score": 52, "homepage": "https://tatsu-lab.github.io/alpaca_eval/", "language": "Jupyter Notebook", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["tatsu-lab/alpaca_eval"], "name": "tatsu-lab/alpaca_eval", "platform": ["python", "cli", "cross-platform"], "pushed_at": "2025-08-09T07:23:36+00:00", "repo": "tatsu-lab/alpaca_eval", "stars": 2012, "tags": ["llm-evaluation", "leaderboard", "instruction-following", "rlhf", "gpt-4-annotator", "win-rate", "chatbot-benchmark", "natural-language-processing"], "topics": ["deep-learning", "evaluation", "foundation-models", "instruction-following", "large-language-models", "leaderboard", "nlp", "rlhf"], "urls": [], "use_cases": ["evaluate an instruction-following LLM automatically", "compare chat LLMs on a leaderboard cheaply and fast", "measure win rates of my model against GPT-4", "build a custom LLM leaderboard", "create a new automatic evaluator for LLM outputs", "benchmark chat models without human annotation", "check how well my model follows user instructions"], "what_it_is": "AlpacaEval is an LLM-based automatic evaluation framework for instruction-following language models, producing win rates against a GPT-4 baseline that correlate strongly (0.98) with human preferences from ChatBot Arena. It includes a public leaderboard, evaluation sets, GPT-4-based auto-annotators, and length-controlled win-rate metrics.", "when_to_avoid": ["you need comprehensive safety or capability testing beyond general instruction following", "you cannot or will not use OpenAI API credits for annotation", "you require a gold-standard human evaluation rather than an LLM-based proxy"], "when_to_choose": ["you need a fast, cheap, human-correlated benchmark for chat/instruction-following LLMs", "you want to submit a model to a recognized community leaderboard", "you want to develop or validate new automatic evaluators or eval sets"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/alpaca_eval", "repo": "tatsu-lab/alpaca_eval", "role": "main", "score": 36}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:06:05.197717+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:01:03.142817+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7f3fc1e4875649a9ce4ea987c8ff16d05b34ce63cdebf15b8b25e815e6c3c090", "fetched_at": "2026-08-28T04:06:05.197717+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tatsu-lab/alpaca_eval"}, {"content_hash": "ef7dda755582ac8ab27e74068fe7731f3f147a609dcba2189392cc63ea17668f", "fetched_at": "2026-08-29T10:41:00.162567+00:00", "kind": "homepage", "missing": false, "url": "https://tatsu-lab.github.io/alpaca_eval/"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:06:05.197717+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:01:03.142817+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7f3fc1e4875649a9ce4ea987c8ff16d05b34ce63cdebf15b8b25e815e6c3c090", "fetched_at": "2026-08-28T04:06:05.197717+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tatsu-lab/alpaca_eval"}, {"content_hash": "ef7dda755582ac8ab27e74068fe7731f3f147a609dcba2189392cc63ea17668f", "fetched_at": "2026-08-29T10:41:00.162567+00:00", "kind": "homepage", "missing": false, "url": "https://tatsu-lab.github.io/alpaca_eval/"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:01:03.142817+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7f3fc1e4875649a9ce4ea987c8ff16d05b34ce63cdebf15b8b25e815e6c3c090", "fetched_at": "2026-08-28T04:06:05.197717+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tatsu-lab/alpaca_eval"}, {"content_hash": "ef7dda755582ac8ab27e74068fe7731f3f147a609dcba2189392cc63ea17668f", "fetched_at": "2026-08-29T10:41:00.162567+00:00", "kind": "homepage", "missing": false, "url": "https://tatsu-lab.github.io/alpaca_eval/"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:06:05.197717+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:06:05.197717+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:06:05.197717+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:01:03.142817+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7f3fc1e4875649a9ce4ea987c8ff16d05b34ce63cdebf15b8b25e815e6c3c090", "fetched_at": "2026-08-28T04:06:05.197717+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tatsu-lab/alpaca_eval"}, {"content_hash": "ef7dda755582ac8ab27e74068fe7731f3f147a609dcba2189392cc63ea17668f", "fetched_at": "2026-08-29T10:41:00.162567+00:00", "kind": "homepage", "missing": false, "url": "https://tatsu-lab.github.io/alpaca_eval/"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:06:05.197717+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:06:05.197717+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:01:03.142817+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7f3fc1e4875649a9ce4ea987c8ff16d05b34ce63cdebf15b8b25e815e6c3c090", "fetched_at": "2026-08-28T04:06:05.197717+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tatsu-lab/alpaca_eval"}, {"content_hash": "ef7dda755582ac8ab27e74068fe7731f3f147a609dcba2189392cc63ea17668f", "fetched_at": "2026-08-29T10:41:00.162567+00:00", "kind": "homepage", "missing": false, "url": "https://tatsu-lab.github.io/alpaca_eval/"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:06:05.197717+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:06:05.197717+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:06:05.197717+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:01:03.142817+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7f3fc1e4875649a9ce4ea987c8ff16d05b34ce63cdebf15b8b25e815e6c3c090", "fetched_at": "2026-08-28T04:06:05.197717+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tatsu-lab/alpaca_eval"}, {"content_hash": "ef7dda755582ac8ab27e74068fe7731f3f147a609dcba2189392cc63ea17668f", "fetched_at": "2026-08-29T10:41:00.162567+00:00", "kind": "homepage", "missing": false, "url": "https://tatsu-lab.github.io/alpaca_eval/"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:06:05.197717+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:06:05.197717+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:01:03.142817+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7f3fc1e4875649a9ce4ea987c8ff16d05b34ce63cdebf15b8b25e815e6c3c090", "fetched_at": "2026-08-28T04:06:05.197717+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tatsu-lab/alpaca_eval"}, {"content_hash": "ef7dda755582ac8ab27e74068fe7731f3f147a609dcba2189392cc63ea17668f", "fetched_at": "2026-08-29T10:41:00.162567+00:00", "kind": "homepage", "missing": false, "url": "https://tatsu-lab.github.io/alpaca_eval/"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:01:03.142817+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7f3fc1e4875649a9ce4ea987c8ff16d05b34ce63cdebf15b8b25e815e6c3c090", "fetched_at": "2026-08-28T04:06:05.197717+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tatsu-lab/alpaca_eval"}, {"content_hash": "ef7dda755582ac8ab27e74068fe7731f3f147a609dcba2189392cc63ea17668f", "fetched_at": "2026-08-29T10:41:00.162567+00:00", "kind": "homepage", "missing": false, "url": "https://tatsu-lab.github.io/alpaca_eval/"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:01:03.142817+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7f3fc1e4875649a9ce4ea987c8ff16d05b34ce63cdebf15b8b25e815e6c3c090", "fetched_at": "2026-08-28T04:06:05.197717+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tatsu-lab/alpaca_eval"}, {"content_hash": "ef7dda755582ac8ab27e74068fe7731f3f147a609dcba2189392cc63ea17668f", "fetched_at": "2026-08-29T10:41:00.162567+00:00", "kind": "homepage", "missing": false, "url": "https://tatsu-lab.github.io/alpaca_eval/"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:01:03.142817+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "7f3fc1e4875649a9ce4ea987c8ff16d05b34ce63cdebf15b8b25e815e6c3c090", "fetched_at": "2026-08-28T04:06:05.197717+00:00", "kind": "readme", "missing": false, "url": "https://github.com/tatsu-lab/alpaca_eval"}, {"content_hash": "ef7dda755582ac8ab27e74068fe7731f3f147a609dcba2189392cc63ea17668f", "fetched_at": "2026-08-29T10:41:00.162567+00:00", "kind": "homepage", "missing": false, "url": "https://tatsu-lab.github.io/alpaca_eval/"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 36, "longevity": 85, "rhythm": 8}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1196, "days_push": 389, "days_rel": 614, "gap_med": null, "n_releases_24m": 1}, "score": 36, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}