Benchgen

Tau2 Retail — Results

RankModelScore
1kolibri-169.9
2claude-opus-4-60.919
3claude-sonnet-4-60.917
4claude-opus-4-50.889
5longcat-flash-thinking-26010.886
6claude-haiku-4-50.832
7gpt-5-20.82
8gpt-50.811
9o30.802
10nova-2-omni0.783
11gpt-5-1-instant0.779

Tau2 Retail — Evaluations

1 phaseActive

No evaluations yet for this benchmark.