Mathematical Reasoning on MATH (test) (ECE and NLL)
7.26ECEProbe
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| ProbeVerifier Type=Probe, Number of Sequences (N)=12026.03 | 7.26 | 0.4391 | |
| MSV 1Verifier Type=MSV, Number of Sequences (N)=12026.03 | 8.49 | 0.4787 | |
| MSV 4Verifier Type=MSV, Number of Sequences (N)=42026.03 | 10.65 | 0.4677 | |
| MSV 16Verifier Type=MSV, Number of Sequences (N)=162026.03 | 11.27 | 0.4615 | |
| MSV 1 + WV 64Verifier Type=MSV, Training Sequences=1, Number of Sequences (N)=64, Weighted Voting (WV)=true2026.03 | 12.02 | 0.7732 | |
| MSV 64Verifier Type=MSV, Number of Sequences (N)=642026.03 | 12.04 | 0.5443 | |
| Probe + WV 64Verifier Type=Probe, Number of Sequences (N)=64, Weighted Voting (WV)=true2026.03 | 12.05 | 0.7788 | |
| MSV 1 + WV 16Verifier Type=MSV, Training Sequences=1, Number of Sequences (N)=16, Weighted Voting (WV)=true2026.03 | 12.9 | 0.9299 | |
| Probe + WV 16Verifier Type=Probe, Number of Sequences (N)=16, Weighted Voting (WV)=true2026.03 | 12.93 | 0.9282 | |
| MSV 1 + WV 4Verifier Type=MSV, Training Sequences=1, Number of Sequences (N)=4, Weighted Voting (WV)=true2026.03 | 16.54 | 1.1819 | |
| Probe + WV 4Verifier Type=Probe, Number of Sequences (N)=4, Weighted Voting (WV)=true2026.03 | 16.55 | 1.1793 |