Mathematical Reasoning on SVAMP (Initial/Final Accuracy & Fix Counts)
73.67Initial Accuracyqwen2.5:1.5b
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| qwen2.5:1.5bModel Role=Initial Reasoner2026.05 | 73.67 | — | — | — | — | — | |
| GUARDEDREPAIRInitial Reasoner=qwen2.5:1.5b, Repair Stage=guarded best-of-32026.05 | — | 88 | 14.33 | 44 | 1 | 33 |