all the models — AI benchmark observatory
← Benchmarks

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.

id tau2-airline · max 1 · 24 models reported

#ModelScore

No scores for this benchmark yet.

Tau2 Airline Leaderboard · all the models