{"slug":"opencompass","name":"opencompass","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://opencompass.org.cn/","repo":"https://github.com/open-compass/opencompass","latestVersion":"0.5.4","latestRelease":"2026-08-26","stars":7533,"starsAsOf":"2026-10-22","description":"OpenCompass is an LLM evaluation platform, supporting a wide range of models from OpenAI, Anthropic, Gemini, Qwen, GLM, DeepSeek, etc, across 100+ datasets covering knowledge, reasoning, coding, science, language, long-context, and safety.","descriptionZh":"上海 AI Lab 大模型评测平台","callMethods":["CLI"],"platforms":[],"addedAt":"2026-10-10","updatedAt":"2026-10-22","topics":["benchmark","evaluation","large-language-model","llm","llm-eval"],"language":"Python","lastPush":"2026-10-21","formerly":null,"packages":[{"registry":"pypi","name":"opencompass","url":"https://pypi.org/project/opencompass/","versionsUrl":"https://pypi.org/project/opencompass/#history","latestVersion":"0.5.4","latestDate":"2026-08-26"}],"recentVersions":[{"version":"0.5.4","date":"2026-08-26","prerelease":false,"url":"https://github.com/open-compass/opencompass/releases/tag/0.5.4","source":"GitHub Release"},{"version":"0.5.3","date":"2026-06-29","prerelease":false,"url":"https://github.com/open-compass/opencompass/releases/tag/0.5.3","source":"GitHub Release"},{"version":"0.5.2","date":"2026-02-14","prerelease":false,"url":"https://github.com/open-compass/opencompass/releases/tag/0.5.2","source":"GitHub Release"},{"version":"0.5.1.post1","date":"2025-10-17","prerelease":false,"url":"https://github.com/open-compass/opencompass/releases/tag/0.5.1.post1","source":"GitHub Release"},{"version":"0.5.1","date":"2025-10-17","prerelease":false,"url":"https://github.com/open-compass/opencompass/releases/tag/0.5.1","source":"GitHub Release"}],"alternatives":["promptfoo","ragas","giskard-oss","osworld","tau2-bench","lmms-eval","vlmevalkit","swe-bench"],"stacks":[],"scenarios":["evaluate-and-monitor"],"problems":[],"reasonZh":"中文/国产模型评测","sources":["profile","priority","oss","github-pool"],"record":"https://aimap.page/api/v1/software/opencompass.json","pages":{"en":"https://aimap.page/en/software/opencompass/","zh-hans":"https://aimap.page/zh-hans/software/opencompass/"}}