Tau3-Bench Airline: leaderboard

τ³-bench airline domain: multimodal, knowledge-aware agentic customer service tasks. New domain in τ³-bench. From Sierra AI.

Metric: Pass@1 (%). Source: taubench.com. Saturation forecast: Around January 2027. 8 models tracked.

Top models

#ModelScoreOverall rank
1Claude Opus 4.584#83
2GPT-5.283#110
3Gemini 3 Flash82.5#99
4GLM-582.5#141
5Qwen 3.5 397B A17B81.5#146
6Gemini 3 Pro80.5#80
7Claude Sonnet 4.572#142

No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.

Interactive version: theaggregate.ai/benchmark?slug=tau3-bench-airline · How It Works · Data refreshed daily, snapshot 2026-10-20.