Question Answering on SciQ (AUC, F95, AUP) benchmark leaderboard · SOTA2 Research

Question Answering on SciQ (AUC, F95, AUP)

87.79AUCSIVR (Ours)

Evaluation Results

Method	Links
SIVR (Ours)2026.04		87.79	54.55	94.14
SIVR2026.04		87.79	54.55	94.14
SAPLMA2026.04		87.41	57.35	92.91
SIVR2026.04		85.7	52.54	93.68
SIVR2026.04		85.7	52.54	93.68
TAD2026.04		85.16	77.59	94.07
TAD2026.04		85.16	77.59	94.07
SATMD + MSP2026.04		84.83	51.67	92.69
Lookback Lens2026.04		83.78	80	90.63
SAPLMA2026.04		83.62	60.34	93
TAD2026.04		83.6	65.67	91.69
TAD2026.04		83.6	65.67	91.69
SIVR2026.04		80.81	63.95	86.03
SIVR2026.04		80.81	63.95	86.03
Lookback Lens2026.04		80.54	77.59	92.09
SE2026.04		79.44	77.08	92.03
SE2026.04		79.01	74.63	87.85
SE2026.04		78.98	81.08	87.83
SATMD + MSP2026.04		78.75	80.7	91.07
Perplexity2026.04		78.59	62.35	85.17
SAR2026.04		78.51	67.57	83.35
Temp-Scaled2026.04		77.87	61.76	83.55
Max Prob2026.04		77.63	62.35	83.97
Entropy2026.04		77.49	66.47	85.13
SATMD + MSP2026.04		77.46	62.2	83.34
TAD2026.04		75.54	84.44	80.9
TAD2026.04		75.54	84.44	80.9
CoE-C2026.04		75.06	83.85	89.14
SAR2026.04		73.98	72.92	89.17
Perplexity2026.04		73.78	72.83	76.2
SAPLMA2026.04		73.55	82.95	79.42
Entropy2026.04		72.98	77.85	75.79
Lookback Lens2026.04		72.93	88.16	83.28
Entropy2026.04		72.85	80.41	85.7
SAR2026.04		72.78	82.09	82.69
Energy2026.04		72.73	79.73	86.21
Max Prob2026.04		72.56	74.2	74.93
Perplexity2026.04		72.42	77.66	84.63
Temp-Scaled2026.04		72.1	73.06	74.59
Energy2026.04		71.65	81.51	75.28
Max Prob2026.04		71.54	78.01	84.05
Temp-Scaled2026.04		70.71	78.35	82.71
CoE-C2026.04		69.56	90.88	82.59
P(True)2026.04		68.76	86.18	80.67
CoE-R2026.04		65.41	94.16	84.73
Energy2026.04		61.56	91.47	75.54
P(True)2026.04		58.66	93.13	79.04
CoE-C2026.04		58.55	93.61	68.29
P(True)2026.04		49.92	94.52	56.88
CoE-R2026.04		41.16	100	53.06
CoE-R2026.04		32.31	100	57.84