Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Answer Verification on AIME terminal answers
Loading...
98.22
AUROC
MSV 64
85.7608
88.9954
92.23
95.4646
Mar 3, 2026
AUROC
Brier Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
AUROC
Brier Score
MSV 64
N sequences=64, Weight...
2026.03
98.22
0.0387
MSV 16
N sequences=16, Weight...
2026.03
97.32
0.0572
MSV 4
N sequences=4, Weighte...
2026.03
96.28
0.0687
MSV 1
N sequences=1, Weighte...
2026.03
94.69
0.0819
Probe
N sequences=1, Weighte...
2026.03
94.61
0.0859
Probe + WV 64
N sequences=64, Weight...
2026.03
92.16
0.1217
MSV 1 + WV 64
N sequences=64, Weight...
2026.03
91.68
0.1264
Probe + WV 16
N sequences=16, Weight...
2026.03
90.92
0.1368
MSV 1 + WV 16
N sequences=16, Weight...
2026.03
90.57
0.1404
MSV 1 + WV 4
N sequences=4, Weighte...
2026.03
86.36
0.2096
Probe + WV 4
N sequences=4, Weighte...
2026.03
86.24
0.21
Feedback
Search any
task
Search any
task