Question Answering on MATH benchmark leaderboard · SOTA2 Research

Question Answering on MATH

83.48AUCSIVR

Evaluation Results

Method	Links
SIVR2026.04		83.48	42.11	86
SIVR2026.04		83.48	42.11	86
SAPLMA2026.04		81.64	70.1	82.49
SAPLMA2026.04		79.87	75.76	69.4
SIVR (Ours)2026.04		79.05	67.57	72.3
SIVR2026.04		79.05	67.57	72.3
TAD2026.04		78.51	68.13	71.86
Energy2026.04		78.1	55.69	73.22
SAPLMA2026.04		78.06	87.1	81.69
SATMD + MSP2026.04		77.71	82.5	78.41
SIVR2026.04		77.56	72.16	77.19
SIVR2026.04		77.56	72.16	77.19
SATMD + MSP2026.04		77.14	71.43	71.22
TAD2026.04		76.96	75.61	69.68
Lookback Lens2026.04		75.54	84.48	71.81
Lookback Lens2026.04		75.54	84.48	71.81
Lookback Lens2026.04		75.19	77.36	78.25
Lookback Lens2026.04		75.19	77.36	78.25
TAD2026.04		74.91	76.06	71.92
SE2026.04		73.58	70.73	76.55
SATMD + MSP2026.04		71.4	64.86	61.95
Entropy2026.04		71.2	71.86	65.12
SAR2026.04		70.87	75.51	73.46
CoE-C2026.04		70.85	84.43	70.53
Energy2026.04		70.85	83.85	68.19
SAR2026.04		70.3	78.43	66.78
SE2026.04		69.83	65.31	72.89
Perplexity2026.04		69.19	77.25	63.29
SAR2026.04		68.84	70.06	78.3
Max Prob2026.04		68.55	76.65	62.31
P(True)2026.04		68.07	81.67	71.3
Temp-Scaled2026.04		67.45	78.44	61.01
SE2026.04		67.27	78.41	68.09
Entropy2026.04		66.26	91.72	66.94
Perplexity2026.04		65.22	91.51	65.77
Max Prob2026.04		64.56	92.55	65.1
Energy2026.04		64.33	88.1	69.14
Temp-Scaled2026.04		64.02	91.51	64.46
Entropy2026.04		62.77	93.89	68.35
Perplexity2026.04		61.66	94.21	67.05
Lookback Lens2026.04		61.06	92.16	50.41
Lookback Lens2026.04		61.06	92.16	50.41
Max Prob2026.04		60.68	93.57	66.27
Temp-Scaled2026.04		60.18	93.57	65.69
CoE-R2026.04		59.5	88.42	65.57
CoE-C2026.04		58.67	90.68	63.95
P(True)2026.04		57.56	94.01	56.37
P(True)2026.04		57.22	98.55	56.84
CoE-C2026.04		55.53	94.41	57.88
CoE-R2026.04		53.39	91.62	50.66
CoE-R2026.04		48.25	97.1	48.8