{"adoption": {"forks": 259, "observed_at": "2026-08-28T04:03:25.124476+00:00", "stars": 1058}, "canonical_url": "https://ross.abutalabs.com/products/bigcode-evaluation-harness", "card": {"archived": false, "artifact_type": "framework", "description": "A framework for the evaluation of autoregressive code generation language models.", "domain": ["large-language-models", "machine-learning", "developer-tools", "programming-languages"], "enriched": true, "function": ["machine-learning", "llm-inference", "benchmarking", "testing"], "health_score": 41, "homepage": null, "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["bigcode-project/bigcode-evaluation-harness"], "name": "bigcode-project/bigcode-evaluation-harness", "platform": ["python"], "pushed_at": "2025-07-22T13:18:09+00:00", "repo": "bigcode-project/bigcode-evaluation-harness", "stars": 1058, "tags": ["code-generation", "llm-evaluation", "humaneval", "benchmark-suite", "huggingface", "linux", "docker", "gpu"], "topics": [], "urls": [], "use_cases": ["evaluate a code generation model on HumanEval", "benchmark an LLM on MBPP and HumanEval+", "compare code models across 18 programming languages with MultiPL-E", "measure robustness of code LLMs with Recode", "run code generation evals in a sandboxed Docker container", "evaluate fill-in-the-middle code completion models"], "what_it_is": "A framework for evaluating autoregressive code generation language models on benchmarks like HumanEval, MBPP, MultiPL-E, and HumanEvalPack. It supports any Hugging Face Hub model, multi-GPU generation with accelerate, and sandboxed Docker execution for reproducible evaluation.", "when_to_avoid": ["you need to evaluate general-purpose (non-code) language models", "you want a hosted evaluation service rather than a local harness", "your model is not available on the Hugging Face Hub"], "when_to_choose": ["you need standardized pass@k evaluation for code generation models", "you want multi-language code benchmark coverage via MultiPL-E or HumanEvalPack", "you need reproducible, sandboxed execution of generated code"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/bigcode-evaluation-harness", "repo": "bigcode-project/bigcode-evaluation-harness", "role": "main", "score": 38}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:25.124476+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:57:45.090663+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a20fcc43054fcf3a4f831509b8e19d3beb91a62a5b24d41936d825e9ccca035d", "fetched_at": "2026-08-28T04:03:25.124476+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bigcode-project/bigcode-evaluation-harness"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:25.124476+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:57:45.090663+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a20fcc43054fcf3a4f831509b8e19d3beb91a62a5b24d41936d825e9ccca035d", "fetched_at": "2026-08-28T04:03:25.124476+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bigcode-project/bigcode-evaluation-harness"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:57:45.090663+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a20fcc43054fcf3a4f831509b8e19d3beb91a62a5b24d41936d825e9ccca035d", "fetched_at": "2026-08-28T04:03:25.124476+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bigcode-project/bigcode-evaluation-harness"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:25.124476+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:25.124476+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:25.124476+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:57:45.090663+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a20fcc43054fcf3a4f831509b8e19d3beb91a62a5b24d41936d825e9ccca035d", "fetched_at": "2026-08-28T04:03:25.124476+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bigcode-project/bigcode-evaluation-harness"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:25.124476+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:25.124476+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:57:45.090663+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a20fcc43054fcf3a4f831509b8e19d3beb91a62a5b24d41936d825e9ccca035d", "fetched_at": "2026-08-28T04:03:25.124476+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bigcode-project/bigcode-evaluation-harness"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:25.124476+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:25.124476+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:25.124476+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:57:45.090663+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a20fcc43054fcf3a4f831509b8e19d3beb91a62a5b24d41936d825e9ccca035d", "fetched_at": "2026-08-28T04:03:25.124476+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bigcode-project/bigcode-evaluation-harness"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:25.124476+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:25.124476+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:57:45.090663+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a20fcc43054fcf3a4f831509b8e19d3beb91a62a5b24d41936d825e9ccca035d", "fetched_at": "2026-08-28T04:03:25.124476+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bigcode-project/bigcode-evaluation-harness"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:57:45.090663+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a20fcc43054fcf3a4f831509b8e19d3beb91a62a5b24d41936d825e9ccca035d", "fetched_at": "2026-08-28T04:03:25.124476+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bigcode-project/bigcode-evaluation-harness"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:57:45.090663+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a20fcc43054fcf3a4f831509b8e19d3beb91a62a5b24d41936d825e9ccca035d", "fetched_at": "2026-08-28T04:03:25.124476+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bigcode-project/bigcode-evaluation-harness"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:57:45.090663+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "a20fcc43054fcf3a4f831509b8e19d3beb91a62a5b24d41936d825e9ccca035d", "fetched_at": "2026-08-28T04:03:25.124476+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bigcode-project/bigcode-evaluation-harness"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 33, "longevity": 100, "rhythm": 8}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1485, "days_push": 407, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 38, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}