{"slug":"lm-evaluation-harness","name":"lm-evaluation-harness","category":"eval","categoryName":"Evaluation, red-teaming & guardrails","audience":["ai-era"],"primary":"ai-era","openClosed":"open","pricing":"open-source","license":"MIT","maintained":"yes","officialUrl":"https://www.eleuther.ai","repo":"https://github.com/EleutherAI/lm-evaluation-harness","latestVersion":"v0.4.13","latestRelease":"2026-08-31","stars":14292,"starsAsOf":"2026-10-22","description":"A framework for few-shot evaluation of language models.","descriptionZh":"语言模型少样本评测框架","callMethods":["CLI"],"platforms":[],"addedAt":"2026-10-10","updatedAt":"2026-10-22","topics":["evaluation-framework","language-model","transformer"],"language":"Python","lastPush":"2026-09-14","formerly":null,"packages":[],"recentVersions":[{"version":"v0.4.13","date":"2026-08-31","prerelease":false,"url":"https://github.com/EleutherAI/lm-evaluation-harness/releases/tag/v0.4.13","source":"GitHub Release"},{"version":"v0.4.12","date":"2026-05-11","prerelease":false,"url":"https://github.com/EleutherAI/lm-evaluation-harness/releases/tag/v0.4.12","source":"GitHub Release"},{"version":"v0.4.11","date":"2026-02-13","prerelease":false,"url":"https://github.com/EleutherAI/lm-evaluation-harness/releases/tag/v0.4.11","source":"GitHub Release"},{"version":"v0.4.10","date":"2026-01-27","prerelease":false,"url":"https://github.com/EleutherAI/lm-evaluation-harness/releases/tag/v0.4.10","source":"GitHub Release"},{"version":"v0.4.9.2","date":"2025-11-26","prerelease":false,"url":"https://github.com/EleutherAI/lm-evaluation-harness/releases/tag/v0.4.9.2","source":"GitHub Release"}],"alternatives":["promptfoo","deepeval","swe-bench","osworld","lighteval","openai-evals","ragas","opencompass"],"stacks":[],"scenarios":["evaluate-and-monitor"],"problems":[],"reasonZh":"模型评测基础","sources":["priority","oss","github-pool"],"record":"https://aimap.page/api/v1/software/lm-evaluation-harness.json","pages":{"en":"https://aimap.page/en/software/lm-evaluation-harness/","zh-hans":"https://aimap.page/zh-hans/software/lm-evaluation-harness/"}}