Share your thoughts, 1 month free Claude Pro on usSee more

Answer Verification on OlympiadBench

89.46AUROC

MSV 16

Updated 1mo ago

Evaluation Results

Method	Links
MSV 16 2026.03		89.46	0.1054
MSV 64 2026.03		88.79	0.1072
MSV 4 2026.03		86.83	0.1197
Probe 2026.03		83.17	0.1478
Probe + WV 4 2026.03		81.86	0.1493
Probe + WV 16 2026.03		81.86	0.1493
Probe + WV 64 2026.03		81.86	0.1493
MSV 1 2026.03		81.69	0.1425
MSV 1 + WV 4 2026.03		81.48	0.1435
MSV 1 + WV 16 2026.03		81.48	0.1435
MSV 1 + WV 64 2026.03		81.48	0.1435