Mathematical Reasoning on MATH L1
62.35Mean@16ME-ICPO
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| ME-ICPOBackbone=Qwen2.5-Math-7B, ME-ICPO=true2026.03 | 62.35 | 57.32 | |
| ME-ICPOBackbone=Qwen2.5-Math-1.5B, ME-ICPO=true2026.03 | 61.19 | 57.06 | |
| Qwen2.5-Math-7BME-ICPO=false2026.03 | 52.62 | 46.98 | |
| Qwen2.5-Math-1.5BME-ICPO=false2026.03 | 49.27 | 44.68 |