List your company

Outcome Reasoning on MalAlgoQA

85.1M' (F1 Mean)GPT-5
56.29263.77171.2578.729May 17, 2025

Evaluation results

MethodLinks
GPT-5Model=GPT-52025.0585.179.6
GPT-o4Model=GPT-o42025.0583.677.8
Llama4-MModel=Llama4-M2025.057468.2
DeepSeekModel=DeepSeek2025.0571.865.1
Gemini2.5Model=Gemini2.52025.0569.662.9
Qwen3Model=Qwen32025.0567.560.9
Llama4-SModel=Llama4-S2025.0557.450.7