Mathematical Reasoning on OlympiadBench (ECE, NLL)
0.0606ECEMSV 16
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| MSV 16Scale=162026.03 | 0.0606 | 0.3546 | |
| MSV 4Scale=42026.03 | 0.0797 | 0.4289 | |
| MSV 64Scale=642026.03 | 0.0868 | 0.377 | |
| MSV 1Scale=12026.03 | 0.0911 | 0.5055 | |
| MSV 1 + WV 4Base Scale=1, Weighted Voting=42026.03 | 0.1292 | 0.4836 | |
| MSV 1 + WV 16Base Scale=1, Weighted Voting=162026.03 | 0.1292 | 0.4836 | |
| MSV 1 + WV 64Base Scale=1, Weighted Voting=642026.03 | 0.1292 | 0.4836 | |
| ProbeContext=Standard Comparison2026.03 | 0.1317 | 0.5206 | |
| Probe + WV 4Weighted Voting=42026.03 | 0.1817 | 0.4885 | |
| Probe + WV 16Weighted Voting=162026.03 | 0.1817 | 0.4885 | |
| Probe + WV 64Weighted Voting=642026.03 | 0.1817 | 0.4885 |