by sierra-research · AI Tool · ★ 1.2k
$\tau$-Bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains 🚀 τ³-bench is here! From text-only to multimodal, knowledge-aware agent evaluation. Voice full-duplex · Knowledge ret
| Stars | 1,213 |
| Forks | 313 |
| Language | Python |
| Category | AI Tool |
| License | MIT |
| Quality Score | 58.678/100 |
| Open Issues | 118 |
| Last Updated | 2026-05-21 |
| Created | 2025-06-09 |
| Platforms | python |
| Est. Tokens | ~22279k |
These tools work well together with tau2-bench for enhanced workflows:
Explore other popular ai tool tools:
tau2-bench is τ-Bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains. It is categorized as a AI Tool with 1.2k GitHub stars.
tau2-bench is primarily written in Python. It covers topics such as ai, benchmark, conversational-agents.
You can find installation instructions and usage details in the tau2-bench GitHub repository at github.com/sierra-research/tau2-bench. The project has 1.2k stars and 313 forks, indicating an active community.
tau2-bench is released under the MIT license, making it free to use and modify according to the license terms.