Benchgen

Tau2 Airline — Results

RankModelScore
1kolibri-176.7
2longcat-flash-thinking-26010.765
3nova-2-omni0.688
4longcat-flash-thinking0.675
5gpt-5-1-instant0.67
6gpt-5-1-thinking0.67
7gpt-5-10.67
8nova-2-pro0.652
9nova-2-lite0.648
10o30.648
11claude-haiku-4-50.636

Tau2 Airline — Phases

1 phaseActive

Phase 1·

Tau2 Airline

Aug 4, 2026
Current