TAU-bench Retail
A benchmark for evaluating tool-agent-user interaction in retail environments. Tests language agents' ability to handle dynamic conversations with users while using domain-specific API tools and following policy guidelines. Evaluates agents on tasks like order cancellations, address changes, and order status checks through multi-turn conversations.
Claude Sonnet 4.5 from Anthropic currently leads the TAU-bench Retail leaderboard with a score of 0.862 across 25 evaluated AI models.
Claude Sonnet 4.5 leads with 86.2%, followed by Claude Opus 4.1 at 82.4% and Claude Opus 4 at 81.4%.
Progress Over Time
Interactive timeline showing model performance evolution on TAU-bench Retail
TAU-bench Retail Leaderboard
| Context | Cost | License | ||||
|---|---|---|---|---|---|---|
| 1 | Anthropic | — | 200K | $3.00 / $15.00 | ||
| 2 | Anthropic | — | — | — | ||
| 3 | Anthropic | — | — | — | ||
| 4 | Anthropic | — | — | — | ||
| 5 | Anthropic | — | — | — | ||
| 6 |  Zhipu AI | 355B | — | — | ||
| 7 | Zhipu AI | 106B | — | — | ||
| 8 |  Alibaba Cloud / Qwen Team | 480B | — | — | ||
| 9 |  OpenAI | — | — | — | ||
| 10 | OpenAI | — | — | — | ||
| 11 | Alibaba Cloud / Qwen Team | 80B | — | — | ||
| 12 | Anthropic | — | — | — | ||
| 13 | OpenAI | — | — | — | ||
| 14 | OpenAI | — | 1.0M | $2.00 / $8.00 | ||
| 15 | Alibaba Cloud / Qwen Team | 235B | — | — | ||
| 15 |  MiniMax | 456B | — | — | ||
| 15 | OpenAI | 117B | 131K | $0.09 / $0.45 | ||
| 18 | MiniMax | 456B | — | — | ||
| 19 | Alibaba Cloud / Qwen Team | 80B | — | — | ||
| 20 | OpenAI | — | 128K | $2.50 / $10.00 | ||
| 21 | OpenAI | — | — | — | ||
| 22 | OpenAI | — | 1.0M | $0.40 / $1.60 | ||
| 23 | OpenAI | 21B | 131K | $0.10 / $0.50 | ||
| 24 | Anthropic | — | — | — | ||
| 25 | OpenAI | — | 1.0M | $0.10 / $0.40 |
FAQ
Common questions about TAU-bench Retail.
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