List your company

Large Model Performance Prediction on Benchmark-side Pattern Shift Math

46.59Average ScoreCPMF
11.666820.733429.838.8666Feb 12, 2026

Evaluation results

MethodLinks
CPMF2026.0246.5936.45-10.14—————
CPMFShift Type=Benchmark-side, Scenario=Math2026.0246.5936.45—48.6344.5553.8952.632.82
PMF2026.0242.0840.36-1.72—————
PMFShift Type=Benchmark-side, Scenario=Math2026.0242.0840.36—44.2139.9461.3357.642.11
STAR2026.0213.0160.6647.65—————
STARShift Type=Benchmark-side, Scenario=Math2026.0213.0160.66—14.711.3186.0977.1818.7