TAU3-Bench
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.
MiMo-V2.5-Pro from Xiaomi currently leads the TAU3-Bench leaderboard with a score of 0.729 across 4 evaluated AI models.
What TAU3-Bench measures
TAU3-Bench is a text benchmark that evaluates large language models on reasoning, agents, and tool calling tasks. LLM Stats tracks 4 models on this benchmark, with a maximum possible score of 1. Current average across reported models is 0.7, with the leader reaching 0.7.
Compare leaders on the best AI for reasoning, best AI for agents and best AI for tool calling leaderboards.
MiMo-V2.5-Pro leads with 72.9%, followed by 
Qwen3.6 Plus at 70.7% and 
GLM-5.1 at 70.6%.
Progress Over Time
Interactive timeline showing model performance evolution on TAU3-Bench
TAU3-Bench Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 | Xiaomi | 1.0T | 1.0M | $0.43 / $0.87 | ||
| 2 |  Alibaba Cloud / Qwen Team | — | 1.0M | $0.50 / $3.00 | ||
| 3 | Zhipu AI | 754B | 200K | $1.40 / $4.40 | ||
| 4 | Alibaba Cloud / Qwen Team | 35B | — | — |
FAQ
Common questions about TAU3-Bench.
More evaluations to explore
Related benchmarks in the same category
A challenging dataset of 448 multiple-choice questions written by domain experts in biology, physics, and chemistry. Questions are Google-proof and extremely difficult, with PhD experts reaching 65% accuracy.
A more robust and challenging multi-task language understanding benchmark that extends MMLU by expanding multiple-choice options from 4 to 10, eliminating trivial questions, and focusing on reasoning-intensive tasks. Features over 12,000 curated questions across 14 domains and causes a 16-33% accuracy drop compared to original MMLU.
All 30 problems from the 2025 American Invitational Mathematics Examination (AIME I and AIME II), testing olympiad-level mathematical reasoning with integer answers from 000-999. Used as an AI benchmark to evaluate large language models' ability to solve complex mathematical problems requiring multi-step logical deductions and structured symbolic reasoning.
Massive Multitask Language Understanding benchmark testing knowledge across 57 diverse subjects including STEM, humanities, social sciences, and professional domains
A verified subset of 500 software engineering problems from real GitHub issues, validated by human annotators for evaluating language models' ability to resolve real-world coding issues by generating patches for Python codebases.
Humanity's Last Exam (HLE) is a multi-modal academic benchmark with 2,500 questions across mathematics, humanities, and natural sciences, designed to test LLM capabilities at the frontier of human knowledge with unambiguous, verifiable solutions