ResearchBenchmarksOutcome Reasoning on CLOMOFollow90.2M' F1 MeanGPT-566.2872.4978.784.91May 17, 2025Evaluation ResultsMethodMethodLinksM' F1 MeanY' F1 MeanGPT-5Model=GPT-5Model=GPT-52025.0590.285.3GPT-o4Model=GPT-o4Model=GPT-o42025.0588.783.9Llama4-MModel=Llama4-MModel=Llama4-M2025.0582.977.2DeepSeekModel=DeepSeekModel=DeepSeek2025.0580.574.3Gemini2.5Model=Gemini2.5Model=Gemini2.52025.0579.372.8Qwen3Model=Qwen3Model=Qwen32025.0577.871.6Llama4-SModel=Llama4-SModel=Llama4-S2025.0567.260.9