reasoning benchmark
Tau-bench Leaderboard
τ-bench: A benchmark for tool-agent-user interaction in real-world domains. Tests language agents' ability to interact with users and follow domain-specific rules through dynamic conversations using API tools and policy guidelines across retail and airline domains. Evaluates consistency and reliability of agent behavior over multiple trials.
Updated Aug 17, 2026
Models6
Model coverage6
MetricScore
EvidenceB
Tau-bench Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelST | Score88.2% | Percentile100.0% | Participants6 | EvidenceC | Evaluated |
| Rank02 | ModelZA | Score87.4% | Percentile80.0% | Participants6 | EvidenceC | Evaluated |
| Rank03 | ModelXI | Score80.3% | Percentile60.0% | Participants6 | EvidenceC | Evaluated |
| Rank04 | ModelZA | Score79.5% | Percentile40.0% | Participants6 | EvidenceC | Evaluated |
| Rank05 | ModelMI | Score77.2% | Percentile20.0% | Participants6 | EvidenceC | Evaluated |
| Rank06 | ModelOP | Score63.0% | Percentile0.0% | Participants6 | EvidenceC | Evaluated |
Tau-bench Highlights
The leading models and scores on this benchmark.
Tau-bench Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for Tau-bench
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis tau-bench AI model leaderboard uses descending score in the benchmark's original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01STStep-3.5-FlashStepFun
- Score
- 88.2%
- Price
- $0.10 input / $0.30 output per 1M tokens
- Speed
- Up to 712 tok/s via StepFun
Strengths
- Ranks #1 of 6 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures Tau-bench, not total model capability
- 02ZAGLM-4.7Zhipu AI
- Score
- 87.4%
- Price
- $0.60 input / $2.2 output per 1M tokens
Strengths
- Ranks #2 of 6 compared models
- 80th percentile on this benchmark
- C evidence result
Considerations
- This result measures Tau-bench, not total model capability
- 03XIMiMo-V2-FlashXiaomi
- Score
- 80.3%
- Price
- $0.14 input / $0.28 output per 1M tokens
Strengths
- Ranks #3 of 6 compared models
- 60th percentile on this benchmark
- C evidence result
Considerations
- This result measures Tau-bench, not total model capability
- 04ZAGLM-4.7-FlashZhipu AI
- Score
- 79.5%
- Speed
- Up to 50 tok/s via ZAI
Strengths
- Ranks #4 of 6 compared models
- 40th percentile on this benchmark
- C evidence result
Considerations
- This result measures Tau-bench, not total model capability
- 05MIMiniMax M2MiniMax
- Score
- 77.2%
- Price
- $0.30 input / $1.2 output per 1M tokens
- Speed
- Up to 103 tok/s via MiniMax
Strengths
- Ranks #5 of 6 compared models
- 20th percentile on this benchmark
- C evidence result
Considerations
- This result measures Tau-bench, not total model capability
Selection summary
Best AI Models for Tau-bench
Step-3.5-Flash currently leads Tau-bench with 88.2%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.
What is Tau-bench?
What Tau-bench measures and how its scores work.
τ-bench: A benchmark for tool-agent-user interaction in real-world domains. Tests language agents' ability to interact with users and follow domain-specific rules through dynamic conversations using API tools and policy guidelines across retail and airline domains. Evaluates consistency and reliability of agent behavior over multiple trials.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- Tau-bench
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- tau-bench|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about Tau-bench.
Which model scores highest on Tau-bench?
Step-3.5-Flash is currently ranked first with 88.2%.
What does Tau-bench measure?
τ-bench: A benchmark for tool-agent-user interaction in real-world domains. Tests language agents' ability to interact with users and follow domain-specific rules through dynamic conversations using API tools and policy guidelines across retail and airline domains. Evaluates consistency and reliability of agent behavior over multiple trials.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
6 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.