Answer Verification on OlympiadBench
89.46AUROCMSV 16
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| MSV 16Sequences=16, Evaluation Protocol=Streaming2026.03 | 89.46 | 0.1054 | |
| MSV 64Sequences=64, Evaluation Protocol=Streaming2026.03 | 88.79 | 0.1072 | |
| MSV 4Sequences=4, Evaluation Protocol=Streaming2026.03 | 86.83 | 0.1197 | |
| ProbeEvaluation Protocol=Streaming2026.03 | 83.17 | 0.1478 | |
| Probe + WV 4Sequences=4, Evaluation Protocol=Weighted Voting2026.03 | 81.86 | 0.1493 | |
| Probe + WV 16Sequences=16, Evaluation Protocol=Weighted Voting2026.03 | 81.86 | 0.1493 | |
| Probe + WV 64Sequences=64, Evaluation Protocol=Weighted Voting2026.03 | 81.86 | 0.1493 | |
| MSV 1Sequences=1, Evaluation Protocol=Streaming2026.03 | 81.69 | 0.1425 | |
| MSV 1 + WV 4Sequences=4, Evaluation Protocol=MSV 1 + Weighted Voting2026.03 | 81.48 | 0.1435 | |
| MSV 1 + WV 16Sequences=16, Evaluation Protocol=MSV 1 + Weighted Voting2026.03 | 81.48 | 0.1435 | |
| MSV 1 + WV 64Sequences=64, Evaluation Protocol=MSV 1 + Weighted Voting2026.03 | 81.48 | 0.1435 |