List your company

Mathematical Reasoning on FALSE Controls 5 theorems, 25 items (pilot)

100Accuracyo4-mini
-4235077May 27, 2026

Evaluation results

MethodLinks
o4-miniType=Reasoning model2026.051000100
DeepSeek R1Type=Reasoning model, Model name=deepseek-reasoner2026.051000100
Gemini 2.5 Flash2026.0596480
Claude Sonnet2026.0596480
GPT-4o-mini2026.0592880
Claude Haiku2026.0592860
GPT-4o2026.05841660
DeepSeek V3Model name=deepseek-chat2026.05683260
Always-TRUEDescription=Oracle2026.0501000