Mathematical Reasoning on AIME Average context 2022-2024
28Accuracy0.7 × RoPE theta × 16 + 0.3 × 1M-Model
Evaluation results
| Method | Links | ||
|---|---|---|---|
| 0.7 × RoPE theta × 16 + 0.3 × 1M-ModelOperation=0.7 × RoPE theta × 16 + 0.3 × 1M-Model, recipe=LCTMerge2025.05 | 28 | 21,592 | |
| RoPE theta × 16Operation=RoPE theta × 162025.05 | 26.67 | 16,179 | |
| RoPE theta × 1Operation=RoPE theta × 12025.05 | 15 | 6,940 |