ResearchBenchmarksOutcome Reasoning on MalAlgoQAFollow85.1M' (F1 Mean)GPT-556.29263.77171.2578.729May 17, 2025Evaluation ResultsMethodMethodLinksM' (F1 Mean)Y' (F1 Mean)GPT-5Model=GPT-5Model=GPT-52025.0585.179.6GPT-o4Model=GPT-o4Model=GPT-o42025.0583.677.8Llama4-MModel=Llama4-MModel=Llama4-M2025.057468.2DeepSeekModel=DeepSeekModel=DeepSeek2025.0571.865.1Gemini2.5Model=Gemini2.5Model=Gemini2.52025.0569.662.9Qwen3Model=Qwen3Model=Qwen32025.0567.560.9Llama4-SModel=Llama4-SModel=Llama4-S2025.0557.450.7