TauC-Bench - Airline (GPT-5.2 User): leaderboard
TauC-Bench (2026) extends the tau2-bench customer-service domains with tasks synthesized by the TASTE pipeline from sampled gold tool-call sequences and evolved with ambiguous or uncooperative users and decoy records. Airline domain, 50 tasks, with a GPT-5.2 user simulator in the tau2-bench harness. Pass^1 in percent, a task counting as solved when the final database state equals the gold state; higher is better.
Metric: pass^1 (times 100, so 0-100): mean per-task success, a task succeeding when the database state after the conversation equals the gold final state, on the 50 generated Airline tasks of TauC-Bench, run in the tau2-bench harness with default settings and a GPT-5.2 user simulator; higher is better. Source: arxiv.org. Saturation forecast: Around February 2027. 4 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 2.5 Flash | 36 | #463 |
| 2 | DeepSeek V3.1 | 36 | #511 |
| 3 | GPT-5.2 | 34 | #185 |
| 4 | Qwen 3 32B | 10 | #972 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=tauc-bench-airline-gpt-5-2-user · How It Works · Data refreshed daily, snapshot 2026-11-21.