# TAU-bench leaderboard

Agentic benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelchoice.dev/leaderboards/benchmarks/agentic-tau-bench

Tool-Agent-User Benchmark. Every model the catalog carries a published TAU-bench value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | Agentic |
| Measure | Domain-specific pass^1 through pass^4 task success |
| Tasks | Airline and retail task sets in the archived 2024 release |
| Difficulty | Policy-constrained, multi-turn customer service |
| Published by | [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://arxiv.org/abs/2406.12045) |

Original TAU-bench tests an agent's tool use and policy compliance in simulated airline and retail conversations. Its pass^k metric asks whether the agent succeeds in every one of k repeated trials.

## TAU-bench ranking

No model in the catalog has a published TAU-bench score. The benchmark is defined by τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains, but the catalog carries no value for it yet. An absent value is shown as absent here rather than as a zero.

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
