ResearchBenchmarksReasoning on Theorem (test)Follow87.3AUROCTRACED85.11685.68386.2586.817Mar 11, 2026Evaluation ResultsMethodMethodLinksAUROCp-valueTRACEDBase Model=DeepSeek-R1Base Model=DeepSeek-R12026.0387.30.008SAPLMABase Model=DeepSeek-R1...Base Model=DeepSeek-R1, Method Status=Runner-up Baseline2026.0385.2—