Which model leads Tau2 airline?

Q: Which model leads Tau2 airline?

GPT-5.1 Instant tops the board at 67

Tau2 airline Leaderboard — Model Scores

Pro Mode — raw scores, one benchmark under the lensofficial card harness

The field · 19 measured

26.567

19 models measured, most on the official card harness. GPT-5.1 Instant tops the board at 67.

19 measured·Lifecycle Updated Oct 8, 2026Score basis

#◆Vendor$/M in$/M out

Leader — ignites whiteField — fill cools with scoreIndependently verified only0 of 19Bars show 26.5–67 · ◆ solid = first-party or better · outlined = arm's-length

01GPT-5.1 InstantOpenAI67———

02GPT-5.1OpenAI67$1.3/M$10.0/M$0.084

03O3OpenAI64.8$2.0/M$8.0/M$0.077

04Claude Haiku 4.5Anthropic63.6$1.0/M$5.0/M$0.047

05GPT-5OpenAI62.6$1.3/M$10.0/M$0.090

06Qwen3 Next 80B A3BAlibaba60.5$0.15/M$1.2/M$0.011

07Claude Opus 4+1 altAnthropic603P$15.0/M$75.0/M$0.750

08LongCat Flash LiteMeituan58———

09EXAONE 4.5 33BLG AI56.5———

10Kimi K2 Instruct+3 altsMoonshot56.5$0.57/M$2.3/M$0.025

11Nemotron 3 Super 120B A12BNVIDIA56.25$0.30/M$0.90/M$0.011

12Claude Sonnet 4+1 altAnthropic55.53P$3.0/M$15.0/M$0.162

13Mercury 2Inception53$0.25/M$0.75/M$0.009

14NVIDIA Nemotron 3 Nano 30B A3BNVIDIA48$0.05/M$0.20/M$0.003

15Qwen3 Next 80B A3B InstructAlibaba45.5$0.15/M$1.2/M$0.015

16GPT-4oOpenAI45.5$5.0/M$15.0/M$0.220

17Qwen3 235B A22B Instruct 2507Alibaba44$0.23/M$0.92/M$0.013

18DeepSeek-V3+1 altDeepSeek393P$0.24/M$0.90/M$0.015

19Qwen3 235B A22B+1 altAlibaba26.53P$0.70/M$2.8/M$0.066

◆ solid = independently verified · aggregator attested · vendor attributed — outlined = cross-reference · source-attributed. Dimmed ◆ = confidence inferred. “+N alts” = alternate disclosures in the drawer with why-demoted. Prices per million tokens; $/point = input price ÷ score. Every row opens its model dossier.

Verification: 19 models scored · 0 independently verified · 4 vendor cross-reference · 15 vendor-reported · 0 with source disagreement. How these tiers are assigned