Mathematical Reasoning on AMC/AIME (out-of-distribution)
40ScoreCOVCAL
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| COVCALn=164, ncal=66, epsilon=0.10, verdict=reject-all (both)2026.05 | 40 | 42.9 | 10.8 |
Loading the SOTA2 catalog…
| Method | Links | |||
|---|---|---|---|---|
| COVCALn=164, ncal=66, epsilon=0.10, verdict=reject-all (both)2026.05 | 40 | 42.9 | 10.8 |