{"adoption": {"forks": 206, "observed_at": "2026-08-28T04:05:38.927357+00:00", "stars": 1804}, "canonical_url": "https://ross.abutalabs.com/products/evalplus", "card": {"archived": false, "artifact_type": "library", "description": "Rigourous evaluation of LLM-synthesized code - NeurIPS 2023 & COLM 2024", "domain": ["large-language-models", "machine-learning", "developer-tools", "testing"], "enriched": true, "function": ["testing", "benchmarking", "llm-inference", "data-generation"], "health_score": 56, "homepage": "https://evalplus.github.io", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["evalplus/evalplus"], "name": "evalplus/evalplus", "platform": ["python", "cli"], "pushed_at": "2025-10-02T22:56:38+00:00", "repo": "evalplus/evalplus", "stars": 1804, "tags": ["code-evaluation", "humaneval-plus", "mbpp-plus", "evalperf", "program-synthesis", "llm-benchmark", "code-generation", "leaderboard", "docker", "linux", "macos"], "topics": ["benchmark", "chatgpt", "gpt-4", "large-language-models", "program-synthesis", "testing", "efficiency"], "urls": [], "use_cases": ["evaluate code generation quality of an LLM", "benchmark my model on HumanEval+ and MBPP+", "measure pass@1 for LLM-synthesized code", "compare code efficiency of LLM outputs", "run rigorous code correctness tests on generated Python", "evaluate long-context code understanding of models"], "what_it_is": "EvalPlus is a Python framework and benchmark suite for rigorously evaluating LLM-synthesized code, providing HumanEval+ and MBPP+ datasets with massively extended test suites plus EvalPerf for code efficiency evaluation. It supports many LLM backends (OpenAI, Anthropic, Gemini, local models) and is widely used by major LLM teams.", "when_to_avoid": ["you need to evaluate natural-language tasks rather than code", "you want a general-purpose unit testing framework for your own codebase", "you need production monitoring of live LLM applications"], "when_to_choose": ["you need rigorous, test-augmented evaluation of LLM code generation", "you want standardized benchmarks recognized by major LLM teams", "you need both correctness and efficiency evaluation of generated code"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/evalplus", "repo": "evalplus/evalplus", "role": "main", "score": 41}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:38.927357+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:21:48.886461+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e347ad34b0549530e801a611602be6ff27e68a9a7a212052affa14650e38fed", "fetched_at": "2026-08-28T04:05:38.927357+00:00", "kind": "readme", "missing": false, "url": "https://github.com/evalplus/evalplus"}, {"content_hash": "08a87169adb91dae589825bd1ae466fc4fa401922b20866f0d3b7f07af9d25b8", "fetched_at": "2026-08-29T11:00:46.231266+00:00", "kind": "homepage", "missing": false, "url": "https://evalplus.github.io"}, {"content_hash": "c13fbdae427c2647f881550c29bd43bb4e38b8d6269a295d96739833a71880df", "fetched_at": "2026-08-29T11:00:46.240025+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/evalplus/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:38.927357+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:21:48.886461+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e347ad34b0549530e801a611602be6ff27e68a9a7a212052affa14650e38fed", "fetched_at": "2026-08-28T04:05:38.927357+00:00", "kind": "readme", "missing": false, "url": "https://github.com/evalplus/evalplus"}, {"content_hash": "08a87169adb91dae589825bd1ae466fc4fa401922b20866f0d3b7f07af9d25b8", "fetched_at": "2026-08-29T11:00:46.231266+00:00", "kind": "homepage", "missing": false, "url": "https://evalplus.github.io"}, {"content_hash": "c13fbdae427c2647f881550c29bd43bb4e38b8d6269a295d96739833a71880df", "fetched_at": "2026-08-29T11:00:46.240025+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/evalplus/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:21:48.886461+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e347ad34b0549530e801a611602be6ff27e68a9a7a212052affa14650e38fed", "fetched_at": "2026-08-28T04:05:38.927357+00:00", "kind": "readme", "missing": false, "url": "https://github.com/evalplus/evalplus"}, {"content_hash": "08a87169adb91dae589825bd1ae466fc4fa401922b20866f0d3b7f07af9d25b8", "fetched_at": "2026-08-29T11:00:46.231266+00:00", "kind": "homepage", "missing": false, "url": "https://evalplus.github.io"}, {"content_hash": "c13fbdae427c2647f881550c29bd43bb4e38b8d6269a295d96739833a71880df", "fetched_at": "2026-08-29T11:00:46.240025+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/evalplus/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:38.927357+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:38.927357+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:38.927357+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:21:48.886461+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e347ad34b0549530e801a611602be6ff27e68a9a7a212052affa14650e38fed", "fetched_at": "2026-08-28T04:05:38.927357+00:00", "kind": "readme", "missing": false, "url": "https://github.com/evalplus/evalplus"}, {"content_hash": "08a87169adb91dae589825bd1ae466fc4fa401922b20866f0d3b7f07af9d25b8", "fetched_at": "2026-08-29T11:00:46.231266+00:00", "kind": "homepage", "missing": false, "url": "https://evalplus.github.io"}, {"content_hash": "c13fbdae427c2647f881550c29bd43bb4e38b8d6269a295d96739833a71880df", "fetched_at": "2026-08-29T11:00:46.240025+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/evalplus/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:38.927357+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:38.927357+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:21:48.886461+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e347ad34b0549530e801a611602be6ff27e68a9a7a212052affa14650e38fed", "fetched_at": "2026-08-28T04:05:38.927357+00:00", "kind": "readme", "missing": false, "url": "https://github.com/evalplus/evalplus"}, {"content_hash": "08a87169adb91dae589825bd1ae466fc4fa401922b20866f0d3b7f07af9d25b8", "fetched_at": "2026-08-29T11:00:46.231266+00:00", "kind": "homepage", "missing": false, "url": "https://evalplus.github.io"}, {"content_hash": "c13fbdae427c2647f881550c29bd43bb4e38b8d6269a295d96739833a71880df", "fetched_at": "2026-08-29T11:00:46.240025+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/evalplus/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:38.927357+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:38.927357+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:38.927357+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:21:48.886461+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e347ad34b0549530e801a611602be6ff27e68a9a7a212052affa14650e38fed", "fetched_at": "2026-08-28T04:05:38.927357+00:00", "kind": "readme", "missing": false, "url": "https://github.com/evalplus/evalplus"}, {"content_hash": "08a87169adb91dae589825bd1ae466fc4fa401922b20866f0d3b7f07af9d25b8", "fetched_at": "2026-08-29T11:00:46.231266+00:00", "kind": "homepage", "missing": false, "url": "https://evalplus.github.io"}, {"content_hash": "c13fbdae427c2647f881550c29bd43bb4e38b8d6269a295d96739833a71880df", "fetched_at": "2026-08-29T11:00:46.240025+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/evalplus/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:38.927357+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:38.927357+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:21:48.886461+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e347ad34b0549530e801a611602be6ff27e68a9a7a212052affa14650e38fed", "fetched_at": "2026-08-28T04:05:38.927357+00:00", "kind": "readme", "missing": false, "url": "https://github.com/evalplus/evalplus"}, {"content_hash": "08a87169adb91dae589825bd1ae466fc4fa401922b20866f0d3b7f07af9d25b8", "fetched_at": "2026-08-29T11:00:46.231266+00:00", "kind": "homepage", "missing": false, "url": "https://evalplus.github.io"}, {"content_hash": "c13fbdae427c2647f881550c29bd43bb4e38b8d6269a295d96739833a71880df", "fetched_at": "2026-08-29T11:00:46.240025+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/evalplus/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:21:48.886461+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e347ad34b0549530e801a611602be6ff27e68a9a7a212052affa14650e38fed", "fetched_at": "2026-08-28T04:05:38.927357+00:00", "kind": "readme", "missing": false, "url": "https://github.com/evalplus/evalplus"}, {"content_hash": "08a87169adb91dae589825bd1ae466fc4fa401922b20866f0d3b7f07af9d25b8", "fetched_at": "2026-08-29T11:00:46.231266+00:00", "kind": "homepage", "missing": false, "url": "https://evalplus.github.io"}, {"content_hash": "c13fbdae427c2647f881550c29bd43bb4e38b8d6269a295d96739833a71880df", "fetched_at": "2026-08-29T11:00:46.240025+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/evalplus/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:21:48.886461+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e347ad34b0549530e801a611602be6ff27e68a9a7a212052affa14650e38fed", "fetched_at": "2026-08-28T04:05:38.927357+00:00", "kind": "readme", "missing": false, "url": "https://github.com/evalplus/evalplus"}, {"content_hash": "08a87169adb91dae589825bd1ae466fc4fa401922b20866f0d3b7f07af9d25b8", "fetched_at": "2026-08-29T11:00:46.231266+00:00", "kind": "homepage", "missing": false, "url": "https://evalplus.github.io"}, {"content_hash": "c13fbdae427c2647f881550c29bd43bb4e38b8d6269a295d96739833a71880df", "fetched_at": "2026-08-29T11:00:46.240025+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/evalplus/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:21:48.886461+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "3e347ad34b0549530e801a611602be6ff27e68a9a7a212052affa14650e38fed", "fetched_at": "2026-08-28T04:05:38.927357+00:00", "kind": "readme", "missing": false, "url": "https://github.com/evalplus/evalplus"}, {"content_hash": "08a87169adb91dae589825bd1ae466fc4fa401922b20866f0d3b7f07af9d25b8", "fetched_at": "2026-08-29T11:00:46.231266+00:00", "kind": "homepage", "missing": false, "url": "https://evalplus.github.io"}, {"content_hash": "c13fbdae427c2647f881550c29bd43bb4e38b8d6269a295d96739833a71880df", "fetched_at": "2026-08-29T11:00:46.240025+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/evalplus/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 45, "longevity": 88, "rhythm": 8}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1236, "days_push": 335, "days_rel": 682, "gap_med": null, "n_releases_24m": 1}, "score": 41, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}