Benchmark
tau-bench
What is tau-bench?
Depends on a simulated user and policy; the simulator model is part of the measurement. Benchmark Radar tracks tau-bench, cited by 3 source documents, with…
- Released
- 2024-06-17
- Evaluates
- tool use
- Openness
- unknown
- Importer
- Model reports
- Reported scores
- 0
Source provenance
- Original evidence https://github.com/sierra-research/tau-bench
tau-bench code
No reported scores are on record for this benchmark yet.
Which sources cite tau-bench?
- GPT-5 OpenAI, 2025-08-07
- Claude Opus 4 and Sonnet 4 Anthropic, 2025-05-22
- Claude 3.7 Sonnet Anthropic, 2025-02-24