reasoning benchmark
TAU-bench Airline Leaderboard
TAU-bench Airline is an airline-domain benchmark for Tool-Agent-User interaction in which language agents handle airline-related tasks and policies through dynamic conversations using API tools.
Updated Sep 5, 2026
Models23
Model coverage23
MetricScore
EvidenceB
TAU-bench Airline Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAN | Score70.00% | Percentile100.00% | Participants23 | EvidenceC | Evaluated |
| Rank02 | ModelMI | Score62.00% | Percentile95.45% | Participants23 | EvidenceC | Evaluated |
| Rank03 | ModelZA | Score60.80% | Percentile90.91% | Participants23 | EvidenceC | Evaluated |
| Rank04 | ModelZA | Score60.40% | Percentile86.36% | Participants23 | EvidenceC | Evaluated |
| Rank05 | ModelAN | Score60.00% | Percentile81.82% | Participants23 | EvidenceC | Evaluated |
| Rank06 | ModelMI | Score60.00% | Percentile77.27% | Participants23 | EvidenceC | Evaluated |
| Rank07 | ModelAC | Score60.00% | Percentile72.73% | Participants23 | EvidenceC | Evaluated |
| Rank08 | ModelAN | Score59.60% | Percentile68.18% | Participants23 | EvidenceC | Evaluated |
| Rank09 | ModelAN | Score58.40% | Percentile63.64% | Participants23 | EvidenceC | Evaluated |
| Rank10 | ModelAN | Score56.00% | Percentile59.09% | Participants23 | EvidenceC | Evaluated |
| Rank11 | ModelOP | Score50.00% | Percentile54.55% | Participants23 | EvidenceC | Evaluated |
| Rank12 | ModelOP | Score50.00% | Percentile50.00% | Participants23 | EvidenceC | Evaluated |
| Rank13 | ModelOP | Score49.40% | Percentile45.45% | Participants23 | EvidenceC | Evaluated |
| Rank14 | ModelOP | Score49.20% | Percentile40.91% | Participants23 | EvidenceC | Evaluated |
| Rank15 | ModelAC | Score49.00% | Percentile36.36% | Participants23 | EvidenceC | Evaluated |
| Rank16 | ModelAN | Score46.00% | Percentile31.82% | Participants23 | EvidenceC | Evaluated |
| Rank17 | ModelAC | Score46.00% | Percentile27.27% | Participants23 | EvidenceC | Evaluated |
| Rank18 | ModelAC | Score44.00% | Percentile22.73% | Participants23 | EvidenceC | Evaluated |
| Rank19 | ModelOP | Score42.80% | Percentile18.18% | Participants23 | EvidenceC | Evaluated |
| Rank20 | ModelOP | Score36.00% | Percentile13.64% | Participants23 | EvidenceC | Evaluated |
| Rank21 | ModelOP | Score32.40% | Percentile9.09% | Participants23 | EvidenceC | Evaluated |
| Rank22 | ModelAN | Score22.80% | Percentile4.55% | Participants23 | EvidenceC | Evaluated |
| Rank23 | ModelOP | Score14.00% | Percentile0.00% | Participants23 | EvidenceC | Evaluated |
TAU-bench Airline Highlights
The leading models and scores on this benchmark.
TAU-bench Airline Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for TAU-bench Airline
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is TAU-bench Airline?
What TAU-bench Airline measures and how its scores work.
TAU-bench Airline is part of τ-bench (TAU-bench), a benchmark for Tool-Agent-User interaction in real-world domains.
It measures language agents' ability to interact with users through dynamic conversations while following domain-specific rules and using API tools, reported as a Score ratio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- TAU-bench Airline
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about TAU-bench Airline.
Which model scores highest on TAU-bench Airline?
Claude Sonnet 4.5 is currently ranked first with 70.00%.
What are the top three models on TAU-bench Airline?
The current leaders are Claude Sonnet 4.5 (70.00%), MiniMax M1 80K (62.00%), and GLM-4.5-Air (60.80%).
Which TAU-bench Airline model has the lowest official input price?
GPT-4.1 nano has the lowest matched official input price at $0.10 input / $0.40 output per 1M tokens.
Which models are fastest among TAU-bench Airline results?
The fastest matched records are GPT-4.1 mini (467.39 tok/s via OpenAI), GPT-4.1 nano (138.14 tok/s via OpenAI), and GPT-4o (132.00 tok/s via OpenAI).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.