Answer Verification on AIME terminal answers
98.22AUROCMSV 64
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| MSV 64N sequences=64, Weighted Voting=False2026.03 | 98.22 | 0.0387 | |
| MSV 16N sequences=16, Weighted Voting=False2026.03 | 97.32 | 0.0572 | |
| MSV 4N sequences=4, Weighted Voting=False2026.03 | 96.28 | 0.0687 | |
| MSV 1N sequences=1, Weighted Voting=False2026.03 | 94.69 | 0.0819 | |
| ProbeN sequences=1, Weighted Voting=False2026.03 | 94.61 | 0.0859 | |
| Probe + WV 64N sequences=64, Weighted Voting=True2026.03 | 92.16 | 0.1217 | |
| MSV 1 + WV 64N sequences=64, Weighted Voting=True2026.03 | 91.68 | 0.1264 | |
| Probe + WV 16N sequences=16, Weighted Voting=True2026.03 | 90.92 | 0.1368 | |
| MSV 1 + WV 16N sequences=16, Weighted Voting=True2026.03 | 90.57 | 0.1404 | |
| MSV 1 + WV 4N sequences=4, Weighted Voting=True2026.03 | 86.36 | 0.2096 | |
| Probe + WV 4N sequences=4, Weighted Voting=True2026.03 | 86.24 | 0.21 |