Mathematical Reasoning on AIME 25 (Peak avg@32 score)
30.31Peak avg@32 ScoreOTB
Evaluation Results
| Method | Links | |
|---|---|---|
| OTBBackbone=Qwen3-8b-Base, Reasoning Paradigm=Single-Turn2026.02 | 30.31 | |
| OGBBackbone=Qwen3-8b-Base, Reasoning Paradigm=Single-Turn2026.02 | 30.1 | |
| OPOBackbone=Qwen3-8b-Base, Reasoning Paradigm=Single-Turn2026.02 | 27.29 | |
| GRPOBackbone=Qwen3-8b-Base, Reasoning Paradigm=Single-Turn2026.02 | 25.31 | |
| RLOOBackbone=Qwen3-8b-Base, Reasoning Paradigm=Single-Turn2026.02 | 24.38 |