Mathematical Reasoning on Omni-MATH (Calibration Metrics)
0.0883ECEMSV 16
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| MSV 16Scale=162026.03 | 0.0883 | — | 0.3888 | |
| MSV 4Scale=42026.03 | 0.0959 | — | 0.4206 | |
| MSV 1 + WV 4Base Scale=1, Weighted Voting=42026.03 | 0.103 | — | 0.455 | |
| MSV 1 + WV 16Base Scale=1, Weighted Voting=162026.03 | 0.103 | — | 0.455 | |
| MSV 1 + WV 64Base Scale=1, Weighted Voting=642026.03 | 0.103 | — | 0.455 | |
| Probe + WV 4Weighted Voting=42026.03 | 0.1104 | — | 0.4407 | |
| Probe + WV 16Weighted Voting=162026.03 | 0.1104 | — | 0.4407 | |
| Probe + WV 64Weighted Voting=642026.03 | 0.1104 | — | 0.4407 | |
| MSV 1Scale=12026.03 | 0.1157 | — | 0.4974 | |
| ProbeN=12026.03 | 0.1206 | 0.2681 | — | |
| MSV 64N=642026.03 | 0.1303 | 0.3434 | — | |
| MSV 64Scale=642026.03 | 0.1316 | — | 0.4296 | |
| MSV 1N=12026.03 | 0.1446 | 0.292 | — | |
| ProbeContext=Standard Comparison2026.03 | 0.1656 | — | 0.5194 | |
| MSV 4N=42026.03 | 0.1695 | 0.341 | — | |
| MSV 16N=162026.03 | 0.1776 | 0.3583 | — | |
| ProbeN=42026.03 | 0.2298 | 0.3997 | — | |
| MSV 1N=42026.03 | 0.2514 | 0.4372 | — | |
| Probe + WV 64N=642026.03 | 0.2888 | 0.5115 | — | |
| MSV 1 + WV 64N=642026.03 | 0.292 | 0.5175 | — | |
| Probe + WV 16N=162026.03 | 0.3195 | 0.5521 | — | |
| MSV 1 + WV 16N=162026.03 | 0.3201 | 0.554 | — | |
| ProbeN=162026.03 | 0.3296 | 0.5635 | — | |
| MSV 1N=162026.03 | 0.3542 | 0.617 | — | |
| ProbeN=642026.03 | 0.4185 | 0.7348 | — | |
| MSV 1 + WV 4N=42026.03 | 0.4354 | 0.7306 | — | |
| Probe + WV 4N=42026.03 | 0.4396 | 0.7359 | — | |
| MSV 1N=642026.03 | 0.4504 | 0.8118 | — |