{"adoption": {"forks": 84, "observed_at": "2026-08-28T04:05:46.342382+00:00", "stars": 1867}, "canonical_url": "https://ross.abutalabs.com/products/ceval", "card": {"archived": false, "artifact_type": "dataset", "description": "Official github repo for C-Eval, a Chinese evaluation suite for foundation models [NeurIPS 2023]", "domain": ["large-language-models", "machine-learning", "education"], "enriched": true, "function": ["benchmarking", "testing", "data-generation"], "health_score": 40, "homepage": "https://cevalbenchmark.com/", "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "stable", "member_repos": ["hkust-nlp/ceval"], "name": "hkust-nlp/ceval", "platform": ["python"], "pushed_at": "2025-07-27T03:55:53+00:00", "repo": "hkust-nlp/ceval", "stars": 1867, "tags": ["chinese-benchmark", "evaluation-suite", "multiple-choice", "foundation-models", "neurips-2023", "llm-evaluation", "natural-language-processing"], "topics": [], "urls": [], "use_cases": ["evaluate a large language model on Chinese-language knowledge", "benchmark my LLM against GPT-4 and ChatGPT on Chinese tasks", "find weaknesses of my model across 52 academic disciplines", "run standardized Chinese multiple-choice evaluations", "compare Chinese capabilities of open-source and proprietary models", "add a Chinese benchmark to my model evaluation pipeline"], "what_it_is": "C-Eval is a comprehensive Chinese evaluation benchmark for foundation models, consisting of 13,948 multiple-choice questions across 52 disciplines and four difficulty levels. The repository provides the dataset, evaluation scripts, and leaderboards for measuring LLM performance on Chinese-language tasks.", "when_to_avoid": ["you need evaluation in languages other than Chinese", "you need open-ended generation or reasoning benchmarks rather than multiple-choice", "you need a lightweight task-specific test rather than a broad academic suite"], "when_to_choose": ["you need a standardized, widely-cited Chinese benchmark for foundation models", "you want multi-discipline coverage from middle school to professional exams", "you want results comparable to published leaderboards and lm-evaluation-harness"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/ceval", "repo": "hkust-nlp/ceval", "role": "main", "score": 44}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:46.342382+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:15:23.446160+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "434c9d665c014e32bc130ecdb72016fa9737e043eebcb5f62c32bce8d6e8305e", "fetched_at": "2026-08-28T04:05:46.342382+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hkust-nlp/ceval"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:46.342382+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:15:23.446160+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "434c9d665c014e32bc130ecdb72016fa9737e043eebcb5f62c32bce8d6e8305e", "fetched_at": "2026-08-28T04:05:46.342382+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hkust-nlp/ceval"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:15:23.446160+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "434c9d665c014e32bc130ecdb72016fa9737e043eebcb5f62c32bce8d6e8305e", "fetched_at": "2026-08-28T04:05:46.342382+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hkust-nlp/ceval"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:46.342382+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:46.342382+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:46.342382+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:15:23.446160+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "434c9d665c014e32bc130ecdb72016fa9737e043eebcb5f62c32bce8d6e8305e", "fetched_at": "2026-08-28T04:05:46.342382+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hkust-nlp/ceval"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:46.342382+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:46.342382+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:15:23.446160+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "434c9d665c014e32bc130ecdb72016fa9737e043eebcb5f62c32bce8d6e8305e", "fetched_at": "2026-08-28T04:05:46.342382+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hkust-nlp/ceval"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:46.342382+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:46.342382+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:46.342382+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:15:23.446160+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "434c9d665c014e32bc130ecdb72016fa9737e043eebcb5f62c32bce8d6e8305e", "fetched_at": "2026-08-28T04:05:46.342382+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hkust-nlp/ceval"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:46.342382+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:46.342382+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:15:23.446160+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "434c9d665c014e32bc130ecdb72016fa9737e043eebcb5f62c32bce8d6e8305e", "fetched_at": "2026-08-28T04:05:46.342382+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hkust-nlp/ceval"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:15:23.446160+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "434c9d665c014e32bc130ecdb72016fa9737e043eebcb5f62c32bce8d6e8305e", "fetched_at": "2026-08-28T04:05:46.342382+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hkust-nlp/ceval"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:15:23.446160+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "434c9d665c014e32bc130ecdb72016fa9737e043eebcb5f62c32bce8d6e8305e", "fetched_at": "2026-08-28T04:05:46.342382+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hkust-nlp/ceval"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:15:23.446160+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "434c9d665c014e32bc130ecdb72016fa9737e043eebcb5f62c32bce8d6e8305e", "fetched_at": "2026-08-28T04:05:46.342382+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hkust-nlp/ceval"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 33, "longevity": 86, "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": 1209, "days_push": 402, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 44, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}