Mathematical Reasoning on GSM-IC
7,651.62Avg Context Length (tokens)PRD
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| PRDType=Full Debate2025.07 | 7,651.62 | — | |
| MLDType=Full Debate2025.07 | 6,287.39 | — | |
| RECONCILEType=Full Debate2025.07 | 6,196.09 | — | |
| ChatEvalType=Full Debate2025.07 | 5,600.22 | — | |
| GDType=Part Debate2025.07 | 3,828.95 | — | |
| NDType=Part Debate2025.07 | 3,149.04 | — | |
| OursType=Part Debate2025.07 | 2,413.35 | — | |
| MaVType=No Debate2025.07 | 1,161.18 | — | |
| ChatEvalType=Full Debate2025.07 | — | 74.33 | |
| CortexDebateType=Ours2025.07 | — | 79.33 | |
| GDType=Part Debate2025.07 | — | 76 | |
| MaVType=No Debate2025.07 | — | 70.33 | |
| MLDType=Full Debate2025.07 | — | 72.67 | |
| NDType=Part Debate2025.07 | — | 73.67 | |
| PRDType=Full Debate2025.07 | — | 77 | |
| RECONCILEType=Full Debate2025.07 | — | 75.67 |