{"slug":"lmms-eval","name":"lmms-eval","category":"eval","categoryName":"Evaluation, red-teaming & guardrails","audience":["ai-era"],"primary":"ai-era","openClosed":"open","pricing":"open-source","license":"Apache-2.0","maintained":"yes","officialUrl":"https://www.lmms-lab.com","repo":"https://github.com/EvolvingLMMs-Lab/lmms-eval","latestVersion":"v0.7.3","latestRelease":"2026-08-28","stars":4462,"starsAsOf":"2026-10-22","description":"One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks","descriptionZh":"多模态模型评测","callMethods":["CLI"],"platforms":[],"addedAt":"2026-10-10","updatedAt":"2026-10-22","topics":["agi","audio-evaluation","benchmark","evaluation","large-language-models","llm-evaluation","multimodal","multimodal-evaluation","video-understanding","vision-language-model","vlm"],"language":"Python","lastPush":"2026-10-17","formerly":null,"packages":[{"registry":"pypi","name":"lmms_eval","url":"https://pypi.org/project/lmms_eval/","versionsUrl":"https://pypi.org/project/lmms_eval/#history","latestVersion":"0.7.3","latestDate":"2026-08-28"}],"recentVersions":[{"version":"v0.7.3","date":"2026-08-28","prerelease":false,"url":"https://github.com/EvolvingLMMs-Lab/lmms-eval/releases/tag/v0.7.3","source":"GitHub Release"},{"version":"v0.7.2","date":"2026-06-24","prerelease":false,"url":"https://github.com/EvolvingLMMs-Lab/lmms-eval/releases/tag/v0.7.2","source":"GitHub Release"},{"version":"v0.7.1","date":"2026-03-15","prerelease":false,"url":"https://github.com/EvolvingLMMs-Lab/lmms-eval/releases/tag/v0.7.1","source":"GitHub Release"},{"version":"v0.7","date":"2026-02-28","prerelease":false,"url":"https://github.com/EvolvingLMMs-Lab/lmms-eval/releases/tag/v0.7","source":"GitHub Release"},{"version":"v0.6.1","date":"2026-02-19","prerelease":false,"url":"https://github.com/EvolvingLMMs-Lab/lmms-eval/releases/tag/v0.6.1","source":"GitHub Release"}],"alternatives":["osworld","promptfoo","opencompass","vlmevalkit","deepeval","ragas","swe-bench","giskard-oss"],"stacks":[],"scenarios":["evaluate-and-monitor"],"problems":[],"reasonZh":"开源大库收录：多模态模型评测","sources":["oss","github-pool"],"record":"https://aimap.page/api/v1/software/lmms-eval.json","pages":{"en":"https://aimap.page/en/software/lmms-eval/","zh-hans":"https://aimap.page/zh-hans/software/lmms-eval/"}}