chat benchmark
Tau2 Airline Leaderboard
Tau2 Airline is a conversational-agent benchmark for airline customer service scenarios in dual-control environments.
Updated Sep 5, 2026
Models24
Model coverage24
MetricScore
EvidenceB
Tau2 Airline Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelME | Score76.50% | Percentile100.00% | Participants24 | EvidenceC | Evaluated |
| Rank02 | ModelAM Nova 2 OmniAmazon | Score68.80% | Percentile95.65% | Participants24 | EvidenceC | Evaluated |
| Rank03 | ModelME | Score67.50% | Percentile91.30% | Participants24 | EvidenceC | Evaluated |
| Rank04 | ModelOP | Score67.00% | Percentile86.96% | Participants24 | EvidenceC | Evaluated |
| Rank05 | ModelOP | Score67.00% | Percentile82.61% | Participants24 | EvidenceC | Evaluated |
| Rank06 | ModelOP | Score67.00% | Percentile78.26% | Participants24 | EvidenceC | Evaluated |
| Rank07 | ModelAMNova 2 ProAmazon | Score65.20% | Percentile73.91% | Participants24 | EvidenceC | Evaluated |
| Rank08 | ModelAMNova 2 LiteAmazon | Score64.80% | Percentile69.57% | Participants24 | EvidenceC | Evaluated |
| Rank09 | ModelOP | Score64.80% | Percentile65.22% | Participants24 | EvidenceC | Evaluated |
| Rank10 | ModelAN | Score63.60% | Percentile60.87% | Participants24 | EvidenceC | Evaluated |
| Rank11 | ModelOP | Score62.60% | Percentile56.52% | Participants24 | EvidenceC | Evaluated |
| Rank12 | ModelAC | Score60.50% | Percentile52.17% | Participants24 | EvidenceC | Evaluated |
| Rank13 | ModelME | Score58.00% | Percentile47.83% | Participants24 | EvidenceC | Evaluated |
| Rank14 | ModelME | Score58.00% | Percentile43.48% | Participants24 | EvidenceC | Evaluated |
| Rank15 | ModelAC | Score58.00% | Percentile39.13% | Participants24 | EvidenceC | Evaluated |
| Rank16 | ModelLA | Score56.50% | Percentile34.78% | Participants24 | EvidenceC | Evaluated |
| Rank17 | ModelMA | Score56.50% | Percentile30.43% | Participants24 | EvidenceC | Evaluated |
| Rank18 | ModelMA | Score56.50% | Percentile26.09% | Participants24 | EvidenceC | Evaluated |
| Rank19 | ModelNV | Score56.25% | Percentile21.74% | Participants24 | EvidenceC | Evaluated |
| Rank20 | ModelIN | Score53.00% | Percentile17.39% | Participants24 | EvidenceC | Evaluated |
| Rank21 | ModelNV | Score48.00% | Percentile13.04% | Participants24 | EvidenceC | Evaluated |
| Rank22 | ModelOP | Score45.50% | Percentile8.70% | Participants24 | EvidenceC | Evaluated |
| Rank23 | ModelAC | Score45.50% | Percentile4.35% | Participants24 | EvidenceC | Evaluated |
| Rank24 | ModelAC | Score44.00% | Percentile0.00% | Participants24 | 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.
What is Tau2 Airline?
What Tau2 Airline measures and how its scores work.
A TAU2 airline domain benchmark in which AI agents and users interact with tools for tasks such as flight booking, modifications, cancellations, and refunds.
It measures agent coordination, communication, and ability to guide user actions, reported as a Score ratio.
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
- chat
- 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 Tau2 Airline.
Which model scores highest on Tau2 Airline?
LongCat-Flash-Thinking-2601 is currently ranked first with 76.50%.
What are the top three models on Tau2 Airline?
The current leaders are LongCat-Flash-Thinking-2601 (76.50%), Nova 2 Omni (68.80%), and LongCat-Flash-Thinking (67.50%).
Which Tau2 Airline model has the lowest official input price?
Nemotron 3 Super (120B A12B) has the lowest matched official input price at $0.20 input / $0.80 output per 1M tokens.
Which models are fastest among Tau2 Airline results?
The fastest matched records are Mercury 2 (346.33 tok/s via Inception), GPT-4o (132.00 tok/s via OpenAI), and GPT-5.1 (100.00 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.