Mathematical Reasoning on AIME 2024 (Mean@16, Accuracy)
30.42Mean@16ME-ICPO
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| ME-ICPOBackbone=Qwen2.5-Math-7B, ME-ICPO=true2026.03 | 30.42 | 30.05 | |
| Qwen2.5-Math-7BME-ICPO=false2026.03 | 11.04 | 11.13 | |
| ME-ICPOBackbone=Qwen2.5-Math-1.5B, ME-ICPO=true2026.03 | 9.79 | 9.82 | |
| Qwen2.5-Math-1.5BME-ICPO=false2026.03 | 6.46 | 6.51 |