{"slug":"tau-bench","name":"tau-bench","category":"eval","categoryName":"Evaluation, red-teaming & guardrails","audience":["ai-era"],"primary":"ai-era","openClosed":"open","pricing":"open-source","license":"MIT","maintained":"stale","officialUrl":"https://github.com/sierra-research/tau-bench","repo":"https://github.com/sierra-research/tau-bench","latestVersion":"","latestRelease":"","stars":1456,"starsAsOf":"2026-10-05","description":"Code and Data for Tau-Bench","descriptionZh":"工具-用户-agent 交互基准","callMethods":["CLI"],"platforms":[],"addedAt":"2026-10-10","updatedAt":"2026-10-05","topics":[],"language":"Python","lastPush":"2026-03-18","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：工具-用户-agent 交互基准","sources":["oss"],"record":"https://aimap.page/api/v1/software/tau-bench.json","pages":{"en":"https://aimap.page/en/software/tau-bench/","zh-hans":"https://aimap.page/zh-hans/software/tau-bench/"}}