Mathematical Reasoning on MATH (test) (Accuracy + Calibration Metrics) benchmark leaderboard · SOTA2 Research

Mathematical Reasoning on MATH (test) (Accuracy + Calibration Metrics)

15.02AccuracyEPICAR

Evaluation Results

Method	Links
EPICAR2026.01		15.02	0.571	0.443	0.361	0.328
EPICAR2026.01		14.42	0.595	0.415	0.362	0.298
EPICAR2026.01		14.38	0.435	0.39	0.361	0.282
STaR2026.01		13.72	0.555	0.492	0.381	0.365
STaR2026.01		13.46	0.57	0.494	0.381	0.365
Base Model2026.01		13.3	0.544	0.496	0.384	0.368
STaR2026.01		13.06	0.415	0.436	0.375	0.312
Base Model2026.01		12.22	0.387	0.448	0.384	0.316
EPICAR2026.01		8.58	0.568	0.108	0.053	0.097
EPICAR2026.01		7.86	0.593	0.167	0.05	0.106
STaR2026.01		7.6	0.562	0.377	0.318	0.217
Base Model2026.01		7.56	0.555	0.376	0.315	0.216
STaR2026.01		7.38	0.562	0.382	0.344	0.219
EPICAR2026.01		6.46	0.571	0.44	0.436	0.257
STaR2026.01		6.24	0.548	0.609	0.456	0.432
Base Model2026.01		5.84	0.529	0.605	0.46	0.424
STaR2026.01		3.54	0.518	0.838	0.515	0.737
EPICAR2026.01		3.53	0.555	0.848	0.514	0.754
STaR2026.01		3.46	0.491	0.838	0.515	0.737
Base Model2026.01		3.3	0.525	0.841	0.516	0.74
EPICAR2026.01		3.3	0.573	0.871	0.532	0.8
EPICAR2026.01		3.14	0.576	0.885	0.534	0.817
STaR2026.01		3.12	0.469	0.826	0.516	0.716
Base Model2026.01		3	0.507	0.827	0.517	0.716