{"adoption": {"forks": 144, "observed_at": "2026-08-28T04:07:21.183247+00:00", "stars": 2775}, "canonical_url": "https://ross.abutalabs.com/products/chain-of-thought-hub", "card": {"archived": false, "artifact_type": "dataset", "description": "Benchmarking large language models' complex reasoning ability with chain-of-thought prompting", "domain": ["large-language-models", "artificial-intelligence", "tutorials"], "enriched": true, "function": ["benchmarking", "prompt-engineering", "machine-learning"], "health_score": 20, "homepage": null, "language": "Jupyter Notebook", "license": "MIT", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["FranxYao/chain-of-thought-hub"], "name": "FranxYao/chain-of-thought-hub", "platform": ["python"], "pushed_at": "2024-08-04T09:40:18+00:00", "repo": "FranxYao/chain-of-thought-hub", "stars": 2775, "tags": ["chain-of-thought", "llm-evaluation", "reasoning-benchmarks", "gsm8k", "math-benchmark", "jupyter-notebooks", "natural-language-processing"], "topics": [], "urls": [], "use_cases": ["benchmark llm reasoning ability", "compare chain-of-thought prompting performance across models", "evaluate a model on gsm8k and math datasets", "track which llm is best at complex reasoning", "find chain-of-thought prompt examples for evaluation", "measure long-context reasoning of large language models"], "what_it_is": "A benchmarking hub and collection of evaluation scripts measuring large language models' complex reasoning ability using chain-of-thought prompting across tasks like GSM8K, MATH, BBH, MMLU, and HumanEval. It accompanies an academic paper and tracks model performance leaderboards over time.", "when_to_avoid": ["you need a production inference or serving tool", "you want general-purpose LLM evaluation beyond reasoning tasks", "you need actively maintained benchmarks with the newest datasets"], "when_to_choose": ["you need standardized complex-reasoning benchmarks for LLMs", "you want curated chain-of-thought prompts and eval scripts", "you are comparing open and closed models on math, coding, or knowledge tasks"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/chain-of-thought-hub", "repo": "FranxYao/chain-of-thought-hub", "role": "main", "score": 30}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:07:21.183247+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T08:16:33.162618+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "339fe4856af63ab7da4ea14be4f2b58cf0615b703ab6f78f6a767b4818dcd002", "fetched_at": "2026-08-28T04:07:21.183247+00:00", "kind": "readme", "missing": false, "url": "https://github.com/FranxYao/chain-of-thought-hub"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:07:21.183247+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T08:16:33.162618+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "339fe4856af63ab7da4ea14be4f2b58cf0615b703ab6f78f6a767b4818dcd002", "fetched_at": "2026-08-28T04:07:21.183247+00:00", "kind": "readme", "missing": false, "url": "https://github.com/FranxYao/chain-of-thought-hub"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T08:16:33.162618+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "339fe4856af63ab7da4ea14be4f2b58cf0615b703ab6f78f6a767b4818dcd002", "fetched_at": "2026-08-28T04:07:21.183247+00:00", "kind": "readme", "missing": false, "url": "https://github.com/FranxYao/chain-of-thought-hub"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:07:21.183247+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:07:21.183247+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:07:21.183247+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T08:16:33.162618+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "339fe4856af63ab7da4ea14be4f2b58cf0615b703ab6f78f6a767b4818dcd002", "fetched_at": "2026-08-28T04:07:21.183247+00:00", "kind": "readme", "missing": false, "url": "https://github.com/FranxYao/chain-of-thought-hub"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:07:21.183247+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:07:21.183247+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T08:16:33.162618+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "339fe4856af63ab7da4ea14be4f2b58cf0615b703ab6f78f6a767b4818dcd002", "fetched_at": "2026-08-28T04:07:21.183247+00:00", "kind": "readme", "missing": false, "url": "https://github.com/FranxYao/chain-of-thought-hub"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:07:21.183247+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:07:21.183247+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:07:21.183247+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T08:16:33.162618+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "339fe4856af63ab7da4ea14be4f2b58cf0615b703ab6f78f6a767b4818dcd002", "fetched_at": "2026-08-28T04:07:21.183247+00:00", "kind": "readme", "missing": false, "url": "https://github.com/FranxYao/chain-of-thought-hub"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:07:21.183247+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:07:21.183247+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T08:16:33.162618+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "339fe4856af63ab7da4ea14be4f2b58cf0615b703ab6f78f6a767b4818dcd002", "fetched_at": "2026-08-28T04:07:21.183247+00:00", "kind": "readme", "missing": false, "url": "https://github.com/FranxYao/chain-of-thought-hub"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T08:16:33.162618+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "339fe4856af63ab7da4ea14be4f2b58cf0615b703ab6f78f6a767b4818dcd002", "fetched_at": "2026-08-28T04:07:21.183247+00:00", "kind": "readme", "missing": false, "url": "https://github.com/FranxYao/chain-of-thought-hub"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T08:16:33.162618+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "339fe4856af63ab7da4ea14be4f2b58cf0615b703ab6f78f6a767b4818dcd002", "fetched_at": "2026-08-28T04:07:21.183247+00:00", "kind": "readme", "missing": false, "url": "https://github.com/FranxYao/chain-of-thought-hub"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T08:16:33.162618+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "339fe4856af63ab7da4ea14be4f2b58cf0615b703ab6f78f6a767b4818dcd002", "fetched_at": "2026-08-28T04:07:21.183247+00:00", "kind": "readme", "missing": false, "url": "https://github.com/FranxYao/chain-of-thought-hub"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 90, "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": 1272, "days_push": 759, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 30, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}