reasoning benchmark
Tau2 Airline Leaderboard
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 17, 2026
Models23
Model coverage23
MetricScore
EvidenceB
Tau2 Airline Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelME | Score76.5% | Percentile100.0% | Participants23 | EvidenceC | Evaluated |
| Rank02 | ModelAM Nova 2 OmniAmazon | Score68.8% | Percentile95.5% | Participants23 | EvidenceC | Evaluated |
| Rank03 | ModelME | Score67.5% | Percentile90.9% | Participants23 | EvidenceC | Evaluated |
| Rank04 | ModelOP | Score67.0% | Percentile86.4% | Participants23 | EvidenceC | Evaluated |
| Rank05 | ModelOP | Score67.0% | Percentile81.8% | Participants23 | EvidenceC | Evaluated |
| Rank06 | ModelOP | Score67.0% | Percentile77.3% | Participants23 | EvidenceC | Evaluated |
| Rank07 | ModelAMNova 2 ProAmazon | Score65.2% | Percentile72.7% | Participants23 | EvidenceC | Evaluated |
| Rank08 | ModelAMNova 2 LiteAmazon | Score64.8% | Percentile68.2% | Participants23 | EvidenceC | Evaluated |
| Rank09 | ModelOP | Score64.8% | Percentile63.6% | Participants23 | EvidenceC | Evaluated |
| Rank10 | ModelAN | Score63.6% | Percentile59.1% | Participants23 | EvidenceC | Evaluated |
| Rank11 | ModelOP | Score62.6% | Percentile54.5% | Participants23 | EvidenceC | Evaluated |
| Rank12 | ModelAC | Score60.5% | Percentile50.0% | Participants23 | EvidenceC | Evaluated |
| Rank13 | ModelME | Score58.0% | Percentile45.5% | Participants23 | EvidenceC | Evaluated |
| Rank14 | ModelME | Score58.0% | Percentile40.9% | Participants23 | EvidenceC | Evaluated |
| Rank15 | ModelAC | Score58.0% | Percentile36.4% | Participants23 | EvidenceC | Evaluated |
| Rank16 | ModelMA | Score56.5% | Percentile31.8% | Participants23 | EvidenceC | Evaluated |
| Rank17 | ModelMA | Score56.5% | Percentile27.3% | Participants23 | EvidenceC | Evaluated |
| Rank18 | ModelNV | Score56.3% | Percentile22.7% | Participants23 | EvidenceC | Evaluated |
| Rank19 | ModelIN | Score53.0% | Percentile18.2% | Participants23 | EvidenceC | Evaluated |
| Rank20 | ModelNV | Score48.0% | Percentile13.6% | Participants23 | EvidenceC | Evaluated |
| Rank21 | ModelOP | Score45.5% | Percentile9.1% | Participants23 | EvidenceC | Evaluated |
| Rank22 | ModelAC | Score45.5% | Percentile4.5% | Participants23 | EvidenceC | Evaluated |
| Rank23 | ModelAC | Score44.0% | Percentile0.0% | Participants23 | EvidenceC | Evaluated |
Tau2 Airline Highlights
The leading models and scores on this benchmark.
Tau2 Airline Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for Tau2 Airline
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis tau2 airline 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.
- 01MELongCat-Flash-Thinking-2601Meituan
- Score
- 76.5%
- Speed
- Up to 100 tok/s via Meituan
Strengths
- Ranks #1 of 23 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures Tau2 Airline, not total model capability
- 02AMNova 2 OmniAmazon
- Score
- 68.8%
Strengths
- Ranks #2 of 23 compared models
- 95th percentile on this benchmark
- C evidence result
Considerations
- This result measures Tau2 Airline, not total model capability
- 03MELongCat-Flash-ThinkingMeituan
- Score
- 67.5%
- Speed
- Up to 100 tok/s via Meituan
Strengths
- Ranks #3 of 23 compared models
- 91th percentile on this benchmark
- C evidence result
Considerations
- This result measures Tau2 Airline, not total model capability
- 04OPGPT-5.1OpenAI
- Score
- 67.0%
- Price
- $1.3 input / $10 output per 1M tokens
- Speed
- Up to 100 tok/s via OpenAI
Strengths
- Ranks #4 of 23 compared models
- 86th percentile on this benchmark
- C evidence result
Considerations
- This result measures Tau2 Airline, not total model capability
- 05OPGPT-5.1 InstantOpenAI
- Score
- 67.0%
- Speed
- Up to 100 tok/s via OpenAI
Strengths
- Ranks #5 of 23 compared models
- 82th percentile on this benchmark
- C evidence result
Considerations
- This result measures Tau2 Airline, not total model capability
Selection summary
Best AI Models for Tau2 Airline
LongCat-Flash-Thinking-2601 currently leads Tau2 Airline with 76.5%. 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 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.