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 7, 2026
Published models23
Registry coverage23
MetricScore
EvidenceB
Tau2 Airline leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
Score distribution
Top published rows on the benchmark's original scale.
Tau2 Airline highlights
The top published results on this benchmark's own scale.
What is Tau2 Airline?
Definition and scoring fields from the benchmark registry.
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. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- Tau2 Airline
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- tau2-airline|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
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 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.