// BENCHMARK

τ-bench benchmark

AI model leaderboard for the τ-bench benchmark. Compare how large language models score on τ-bench, see the full ranking, and understand what this AI benchmark measures. Multi-turn agent benchmark simulating realistic customer-service tool environments.

Leaderboard

No model scores reported yet.

Frequently asked questions about τ-bench

What is the τ-bench benchmark?

Multi-turn agent benchmark simulating realistic customer-service tool environments.

How is the τ-bench benchmark scored?

τ-bench is scored using the pass^1 (%) metric, where a higher score is better. The maximum achievable score is 100.000. GenAIList aggregates reported scores from model providers and papers into a single ranked leaderboard.

Which AI model scores highest on τ-bench?

No model scores have been reported for τ-bench yet. Check back as the leaderboard is updated.

Is a higher τ-bench score better?

Yes. On τ-bench a higher score indicates better performance, so models near the top of the leaderboard are the strongest.