List your company

Outcome Reasoning on CRASS

92.1M' (F1 Mean)GPT-5
69.2275.1681.187.04May 17, 2025

Evaluation results

MethodLinks
GPT-5Model=GPT-52025.0592.188
GPT-o4Model=GPT-o42025.0590.586.2
Llama4-MModel=Llama4-M2025.0584.979.5
DeepSeekModel=DeepSeek2025.0582.977.1
Gemini2.5Model=Gemini2.52025.0581.775.2
Qwen3Model=Qwen32025.0580.573.9
Llama4-SModel=Llama4-S2025.0570.163.5