{"slug":"livebench","name":"LiveBench","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://github.com/LiveBench/LiveBench","repo":"https://github.com/LiveBench/LiveBench","latestVersion":"","latestRelease":"","stars":1336,"starsAsOf":"2026-10-04","description":"LiveBench: A Challenging, Contamination-Free LLM Benchmark","descriptionZh":"防污染动态 LLM 基准","callMethods":["CLI"],"platforms":[],"addedAt":"2026-10-10","updatedAt":"2026-10-04","topics":[],"language":"Python","lastPush":"2026-09-29","formerly":null,"packages":[],"recentVersions":[],"alternatives":["promptfoo","openai-evals","deepeval","ragas","lm-evaluation-harness","opencompass","swe-bench","giskard-oss"],"stacks":[],"scenarios":["evaluate-and-monitor"],"problems":[],"reasonZh":"开源大库收录：防污染动态 LLM 基准","sources":["oss"],"record":"https://aimap.page/api/v1/software/livebench.json","pages":{"en":"https://aimap.page/en/software/livebench/","zh-hans":"https://aimap.page/zh-hans/software/livebench/"}}