List your company
ResearchFormerly WizWand

Outcome Reasoning on Open-Critic

75.3M' (F1 Mean)GPT-5
44.6252.58560.5568.515May 17, 2025
Updated 8mo ago

Evaluation results

MethodLinks
GPT-5Model=GPT-52025.0575.369.4
GPT-o4Model=GPT-o42025.0573.867.5
Llama4-MModel=Llama4-M2025.0561.554.7
DeepSeekModel=DeepSeek2025.0557.250.6
Qwen3Model=Qwen32025.055649.4
Gemini2.5Model=Gemini2.52025.0553.747.3
Llama4-SModel=Llama4-S2025.0545.839.2