ResearchBenchmarksTask performance and governance on S1 HighRiskFollow0.5CDLR10.12040.218950.31750.41605May 14, 2026Evaluation ResultsMethodMethodLinksCDLDIUMCCF1 ScoreAccuracyGORR1Regime=R1Regime=R12026.050.50.280.43746.142.1—R2Regime=R2Regime=R22026.050.1350.7240.8385.686.8—