reasoning benchmark
Tau2 Airline
TAU2 airline domain benchmark for evaluating conversational agents in dual-control environments where both AI agents and users interact with tools in airline customer service scenarios. Tests agent coordination, communication, and ability to guide user actions in tasks like flight booking, modifications, cancellations, and refunds.
Updated Aug 11, 2026
Models23
Model coverage23
MetricScore
EvidenceB
Tau2 Airline Ranking
Higher score ranks better on this benchmark.
Tau2 Airline Score Distribution
A closer view of the leading scores on this benchmark.
Tau2 Airline Highlights
The leading models and scores on this benchmark.
What is Tau2 Airline?
What Tau2 Airline measures and how its scores work.
TAU2 airline domain benchmark for evaluating conversational agents in dual-control environments where both AI agents and users interact with tools in airline customer service scenarios. Tests agent coordination, communication, and ability to guide user actions in tasks like flight booking, modifications, cancellations, and refunds.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- Tau2 Airline
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- tau2-airline|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about Tau2 Airline.
Which model scores highest on Tau2 Airline?
LongCat-Flash-Thinking-2601 is currently ranked first with 76.5%.
What does Tau2 Airline measure?
TAU2 airline domain benchmark for evaluating conversational agents in dual-control environments where both AI agents and users interact with tools in airline customer service scenarios. Tests agent coordination, communication, and ability to guide user actions in tasks like flight booking, modifications, cancellations, and refunds.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
23 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.