TAU3-Bench

reasoning

Multilingual: no

TAU3-Bench is a benchmark for evaluating general-purpose agent capabilities, testing models on multi-turn interactions with simulated user models, retrieval, and complex decision-making scenarios.

Methodology

Imported from llm-stats public benchmark metadata. Modality: text. Max score: 1. Categories: agents, reasoning, tool_calling. Language: en. Verified by llm-stats: no.