Mathematical Reasoning on AMC (Mean@16, Accuracy)
47.06Mean@16ME-ICPO
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| ME-ICPOBackbone=Qwen2.5-Math-7B, ME-ICPO=true2026.03 | 47.06 | 47.2 | |
| Qwen2.5-Math-7BME-ICPO=false2026.03 | 41.42 | 41.33 | |
| ME-ICPOBackbone=Qwen2.5-Math-1.5B, ME-ICPO=true2026.03 | 33.58 | 33.73 | |
| Qwen2.5-Math-1.5BME-ICPO=false2026.03 | 30.42 | 30.25 |