{"adoption": {"forks": 159, "observed_at": "2026-08-28T04:03:25.818452+00:00", "stars": 1060}, "canonical_url": "https://ross.abutalabs.com/products/arena-hard-auto", "card": {"archived": false, "artifact_type": "dataset", "description": "Arena-Hard-Auto: An automatic LLM benchmark. ", "domain": ["large-language-models", "machine-learning", "artificial-intelligence", "testing"], "enriched": true, "function": ["benchmarking", "llm-inference"], "health_score": 37, "homepage": null, "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["lmarena/arena-hard-auto"], "name": "lmarena/arena-hard-auto", "platform": ["python", "cli"], "pushed_at": "2025-06-21T04:44:12+00:00", "repo": "lmarena/arena-hard-auto", "stars": 1060, "tags": ["llm-evaluation", "llm-benchmark", "chatbot-arena", "model-ranking", "llm-judge", "leaderboard", "evaluation"], "topics": [], "urls": [], "use_cases": ["benchmark my instruction-tuned LLM automatically", "estimate how a model ranks on Chatbot Arena before deployment", "compare LLMs on hard open-ended prompts", "evaluate models on creative writing tasks", "run LLM-as-judge evaluations", "measure model separability on challenging queries"], "what_it_is": "Arena-Hard-Auto is an automatic benchmark for evaluating instruction-tuned LLMs using challenging real-world prompts and LLM-based judges (GPT-4.1, Gemini-2.5). It provides a cheap, fast approximation of Chatbot Arena human preference rankings with high correlation to LMArena results.", "when_to_avoid": ["you need deterministic task-specific benchmarks like MMLU or code correctness tests", "you cannot afford API calls to commercial judge models", "you need human preference data rather than LLM-judge approximations"], "when_to_choose": ["you need a fast, cheap proxy for human preference evaluation of chat LLMs", "you want to predict Chatbot Arena performance before release", "you need challenging real-world prompts including software engineering, math, and creative writing"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/arena-hard-auto", "repo": "lmarena/arena-hard-auto", "role": "main", "score": 39}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:25.818452+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:56:57.957454+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5d04bc38063fc8836875440bbcfb0e69dcf67b2c10d8f6321c78b9e927ec1e49", "fetched_at": "2026-08-28T04:03:25.818452+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lmarena/arena-hard-auto"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:25.818452+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:56:57.957454+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5d04bc38063fc8836875440bbcfb0e69dcf67b2c10d8f6321c78b9e927ec1e49", "fetched_at": "2026-08-28T04:03:25.818452+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lmarena/arena-hard-auto"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:56:57.957454+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5d04bc38063fc8836875440bbcfb0e69dcf67b2c10d8f6321c78b9e927ec1e49", "fetched_at": "2026-08-28T04:03:25.818452+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lmarena/arena-hard-auto"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:25.818452+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:25.818452+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:25.818452+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:56:57.957454+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5d04bc38063fc8836875440bbcfb0e69dcf67b2c10d8f6321c78b9e927ec1e49", "fetched_at": "2026-08-28T04:03:25.818452+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lmarena/arena-hard-auto"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:25.818452+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:25.818452+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:56:57.957454+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5d04bc38063fc8836875440bbcfb0e69dcf67b2c10d8f6321c78b9e927ec1e49", "fetched_at": "2026-08-28T04:03:25.818452+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lmarena/arena-hard-auto"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:25.818452+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:25.818452+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:25.818452+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:56:57.957454+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5d04bc38063fc8836875440bbcfb0e69dcf67b2c10d8f6321c78b9e927ec1e49", "fetched_at": "2026-08-28T04:03:25.818452+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lmarena/arena-hard-auto"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:25.818452+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:25.818452+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:56:57.957454+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5d04bc38063fc8836875440bbcfb0e69dcf67b2c10d8f6321c78b9e927ec1e49", "fetched_at": "2026-08-28T04:03:25.818452+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lmarena/arena-hard-auto"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:56:57.957454+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5d04bc38063fc8836875440bbcfb0e69dcf67b2c10d8f6321c78b9e927ec1e49", "fetched_at": "2026-08-28T04:03:25.818452+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lmarena/arena-hard-auto"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:56:57.957454+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5d04bc38063fc8836875440bbcfb0e69dcf67b2c10d8f6321c78b9e927ec1e49", "fetched_at": "2026-08-28T04:03:25.818452+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lmarena/arena-hard-auto"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:56:57.957454+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "5d04bc38063fc8836875440bbcfb0e69dcf67b2c10d8f6321c78b9e927ec1e49", "fetched_at": "2026-08-28T04:03:25.818452+00:00", "kind": "readme", "missing": false, "url": "https://github.com/lmarena/arena-hard-auto"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 27, "longevity": 73, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1033, "days_push": 438, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 39, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}