{"adoption": {"forks": 138, "observed_at": "2026-08-28T04:04:03.607696+00:00", "stars": 1229}, "canonical_url": "https://ross.abutalabs.com/products/longbench", "card": {"archived": false, "artifact_type": "dataset", "description": "LongBench v2 and LongBench (ACL 25'&24')", "domain": ["large-language-models", "machine-learning"], "enriched": true, "function": ["benchmarking", "llm-inference", "nlp"], "health_score": 21, "homepage": "https://longbench2.github.io", "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["THUDM/LongBench"], "name": "THUDM/LongBench", "platform": ["python"], "pushed_at": "2025-01-15T02:04:04+00:00", "repo": "THUDM/LongBench", "stars": 1229, "tags": ["long-context", "evaluation", "llm-benchmark", "multiple-choice", "leaderboard", "natural-language-processing", "algorithms"], "topics": ["benchmark", "llm", "longtext", "long-context"], "urls": [], "use_cases": ["evaluate llm long-context understanding", "benchmark models on long document qa", "compare llms on 128k+ token contexts", "test long-context reasoning ability of a model", "measure effect of inference-time compute on long-context tasks", "find leaderboard results for long-context benchmarks"], "what_it_is": "LongBench is a benchmark suite (v1 and v2) for evaluating large language models on long-context understanding and reasoning tasks, with contexts from 8k to 2M words across six task categories. It includes 503 challenging multiple-choice questions in v2, plus datasets, evaluation code, and a public leaderboard.", "when_to_avoid": ["you need open-ended generation quality evaluation rather than multiple-choice accuracy", "you need short-context or general-purpose benchmarks", "you need a training dataset rather than an evaluation benchmark"], "when_to_choose": ["you need a standardized, reliable benchmark for long-context LLM evaluation", "you want multiple-choice scoring for reproducible comparisons", "you need contexts spanning 8k to 2M words across diverse task types"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/longbench", "repo": "THUDM/LongBench", "role": "main", "score": 29}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:03.607696+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:15:05.508657+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3333e97e294594bc11ceb34c8a689ccea04c9ab8b3160a3aaa022f1b1987ae44", "fetched_at": "2026-08-28T04:04:03.607696+00:00", "kind": "readme", "missing": false, "url": "https://github.com/THUDM/LongBench"}, {"content_hash": "a76881d23555ed1f6f688d75da633a6482f3554daa392040e5471baaf9b8befd", "fetched_at": "2026-08-29T12:22:56.041719+00:00", "kind": "homepage", "missing": false, "url": "https://longbench2.github.io"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:03.607696+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:15:05.508657+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3333e97e294594bc11ceb34c8a689ccea04c9ab8b3160a3aaa022f1b1987ae44", "fetched_at": "2026-08-28T04:04:03.607696+00:00", "kind": "readme", "missing": false, "url": "https://github.com/THUDM/LongBench"}, {"content_hash": "a76881d23555ed1f6f688d75da633a6482f3554daa392040e5471baaf9b8befd", "fetched_at": "2026-08-29T12:22:56.041719+00:00", "kind": "homepage", "missing": false, "url": "https://longbench2.github.io"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:15:05.508657+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3333e97e294594bc11ceb34c8a689ccea04c9ab8b3160a3aaa022f1b1987ae44", "fetched_at": "2026-08-28T04:04:03.607696+00:00", "kind": "readme", "missing": false, "url": "https://github.com/THUDM/LongBench"}, {"content_hash": "a76881d23555ed1f6f688d75da633a6482f3554daa392040e5471baaf9b8befd", "fetched_at": "2026-08-29T12:22:56.041719+00:00", "kind": "homepage", "missing": false, "url": "https://longbench2.github.io"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:03.607696+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:03.607696+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:03.607696+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:15:05.508657+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3333e97e294594bc11ceb34c8a689ccea04c9ab8b3160a3aaa022f1b1987ae44", "fetched_at": "2026-08-28T04:04:03.607696+00:00", "kind": "readme", "missing": false, "url": "https://github.com/THUDM/LongBench"}, {"content_hash": "a76881d23555ed1f6f688d75da633a6482f3554daa392040e5471baaf9b8befd", "fetched_at": "2026-08-29T12:22:56.041719+00:00", "kind": "homepage", "missing": false, "url": "https://longbench2.github.io"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:03.607696+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:03.607696+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:15:05.508657+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3333e97e294594bc11ceb34c8a689ccea04c9ab8b3160a3aaa022f1b1987ae44", "fetched_at": "2026-08-28T04:04:03.607696+00:00", "kind": "readme", "missing": false, "url": "https://github.com/THUDM/LongBench"}, {"content_hash": "a76881d23555ed1f6f688d75da633a6482f3554daa392040e5471baaf9b8befd", "fetched_at": "2026-08-29T12:22:56.041719+00:00", "kind": "homepage", "missing": false, "url": "https://longbench2.github.io"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:03.607696+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:03.607696+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:03.607696+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:15:05.508657+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3333e97e294594bc11ceb34c8a689ccea04c9ab8b3160a3aaa022f1b1987ae44", "fetched_at": "2026-08-28T04:04:03.607696+00:00", "kind": "readme", "missing": false, "url": "https://github.com/THUDM/LongBench"}, {"content_hash": "a76881d23555ed1f6f688d75da633a6482f3554daa392040e5471baaf9b8befd", "fetched_at": "2026-08-29T12:22:56.041719+00:00", "kind": "homepage", "missing": false, "url": "https://longbench2.github.io"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:03.607696+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:03.607696+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:15:05.508657+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3333e97e294594bc11ceb34c8a689ccea04c9ab8b3160a3aaa022f1b1987ae44", "fetched_at": "2026-08-28T04:04:03.607696+00:00", "kind": "readme", "missing": false, "url": "https://github.com/THUDM/LongBench"}, {"content_hash": "a76881d23555ed1f6f688d75da633a6482f3554daa392040e5471baaf9b8befd", "fetched_at": "2026-08-29T12:22:56.041719+00:00", "kind": "homepage", "missing": false, "url": "https://longbench2.github.io"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:15:05.508657+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3333e97e294594bc11ceb34c8a689ccea04c9ab8b3160a3aaa022f1b1987ae44", "fetched_at": "2026-08-28T04:04:03.607696+00:00", "kind": "readme", "missing": false, "url": "https://github.com/THUDM/LongBench"}, {"content_hash": "a76881d23555ed1f6f688d75da633a6482f3554daa392040e5471baaf9b8befd", "fetched_at": "2026-08-29T12:22:56.041719+00:00", "kind": "homepage", "missing": false, "url": "https://longbench2.github.io"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:15:05.508657+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3333e97e294594bc11ceb34c8a689ccea04c9ab8b3160a3aaa022f1b1987ae44", "fetched_at": "2026-08-28T04:04:03.607696+00:00", "kind": "readme", "missing": false, "url": "https://github.com/THUDM/LongBench"}, {"content_hash": "a76881d23555ed1f6f688d75da633a6482f3554daa392040e5471baaf9b8befd", "fetched_at": "2026-08-29T12:22:56.041719+00:00", "kind": "homepage", "missing": false, "url": "https://longbench2.github.io"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:15:05.508657+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3333e97e294594bc11ceb34c8a689ccea04c9ab8b3160a3aaa022f1b1987ae44", "fetched_at": "2026-08-28T04:04:03.607696+00:00", "kind": "readme", "missing": false, "url": "https://github.com/THUDM/LongBench"}, {"content_hash": "a76881d23555ed1f6f688d75da633a6482f3554daa392040e5471baaf9b8befd", "fetched_at": "2026-08-29T12:22:56.041719+00:00", "kind": "homepage", "missing": false, "url": "https://longbench2.github.io"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 1, "longevity": 80, "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": 1131, "days_push": 596, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 29, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}