ResearchBenchmarksMathematical Reasoning on Average HMMT2025, GPQA-D, AIME2024, AIME2025, BRUMO2025Mathematical Reasoning on Average HMMT2025, GPQA-D, AIME2024, AIME2025, BRUMO2025Follow77.84Average AccuracyDIS-GMM*76.477676.831377.18577.5387Mar 4, 2026Evaluation resultsMethodMethodLinksAverage AccuracyDIS-GMM*Model=DeepSeek-R1-8B,...Model=DeepSeek-R1-8B, SelfStepConf=true2026.0377.84DIS-GMM*Model=Qwen3-32B, Think...Model=Qwen3-32B, Thinking mode=false, SelfStepConf=true2026.0376.53