ResearchBenchmarksLarge Model Performance Prediction on Benchmark-side Pattern Shift ChineseFollow42.16Average ScorePMF13.40420.869528.33535.8005Feb 12, 2026Evaluation ResultsMethodMethodLinksAverage ScoreRank Avg (%)Total Metric ValuePMF2026.0242.1635.39-6.77CPMF2026.0239.3650.0410.68STAR2026.0214.5151.0336.52