Mathematical Reasoning on MATH (Context Length)
8,849.7Avg Context Length (tokens)PRD
Evaluation Results
| Method | Links | |
|---|---|---|
| PRDType=Full Debate2025.07 | 8,849.7 | |
| PRDType=Full Debate2025.07 | 8,652.23 | |
| RECONCILEType=Full Debate2025.07 | 6,723.84 | |
| RECONCILEType=Full Debate2025.07 | 6,574.29 | |
| MLDType=Full Debate2025.07 | 6,408.39 | |
| MLDType=Full Debate2025.07 | 6,397.97 | |
| ChatEvalType=Full Debate2025.07 | 5,571.07 | |
| ChatEvalType=Full Debate2025.07 | 5,394.71 | |
| GDType=Part Debate2025.07 | 4,217.23 | |
| NDType=Part Debate2025.07 | 4,207.18 | |
| NDType=Part Debate2025.07 | 4,175.27 | |
| GDType=Part Debate2025.07 | 4,139.04 | |
| OursType=Part Debate2025.07 | 3,355.2 | |
| OursType=Part Debate2025.07 | 3,262.79 | |
| MaVType=No Debate2025.07 | 1,316.85 | |
| MaVType=No Debate2025.07 | 1,277.73 |