tau-bench: τ-bench
Multi-turn tool-use benchmark for agent behavior in realistic retail and airline customer-service tasks, measuring whether models complete tasks through APIs while following policy constraints.High benchmark score alone doesn't make a model the right pick — weigh it against pricing, API availability, and release date.
Models ranked
29
tracked on this benchmark
Score band
95.3 – 61.1
best → lowest tracked
Snapshot trend
-7.71
May 5 → Jun 7 · 13 models
Leaderboard
Tracked models ranked by % Task Success (higher is better).
How to read this benchmark
This benchmark scores models where higher is better. Scores are useful for directional filtering and shortlisting — not for universal quality ranking. Prefer benchmarks closest to your workload, then validate the linked model pages for pricing, context window, and provider availability.
Trust this score when
- There is a fresh timestamped snapshot (or multiple snapshots) for this benchmark.
- The model list covers the same version family you can actually deploy today.
- Top candidates overlap with your required routing and feature requirements.
Be cautious when
- There is only one benchmark snapshot or the dataset appears stale.
- The benchmark metric direction is opposite of your decision objective.
- The score difference between options is narrow and likely within implementation variance.
FAQ
What does the tau-bench benchmark measure?
Multi-turn tool-use benchmark for agent behavior in realistic retail and airline customer-service tasks, measuring whether models complete tasks through APIs while following policy constraints. On this page it ranks 29 tracked models where higher is better.
Is a higher τ-bench score always better?
For this benchmark, higher is better. A high score helps you shortlist, but confirm pricing, context window, and provider availability on each model page before committing — the top scorer is not always the right pick for your workload or budget.
How current is this τ-bench data?
This benchmark was last reviewed on Apr 26, 2026. The tracked score average moved -7.71 points across the last 3 snapshots.
Related benchmarks
Last reviewed: Apr 26, 2026