List your company

Model Ranking Correlation Analysis on MMMU (10%-50% subsets)

0.96Spearman Correlation (10% Subset)M2IRT
0.1280.3440.560.776Mar 3, 2026

Evaluation results

MethodLinks
M2IRT2026.030.960.960.960.970.96
M3IRT2026.030.890.920.920.930.93
FlashEval2026.030.790.790.790.80.8
Random2026.030.770.80.820.820.81
IRT2026.030.50.360.380.350.12
TinyBenchmarks2026.030.430.50.560.610.67
MIRT2026.030.160.330.470.610.69