Single-Turn Mathematical Reasoning on MATH500
93.43Peak Avg ScoreOTB
Evaluation Results
| Method | Links | |
|---|---|---|
| OTBBackbone=Qwen3-8b-Base, Reasoning Paradigm=Single-Turn2026.02 | 93.43 | |
| OPOBackbone=Qwen3-8b-Base, Reasoning Paradigm=Single-Turn2026.02 | 93.31 | |
| OGBBackbone=Qwen3-8b-Base, Reasoning Paradigm=Single-Turn2026.02 | 90.75 | |
| RLOOBackbone=Qwen3-8b-Base, Reasoning Paradigm=Single-Turn2026.02 | 90.56 | |
| GRPOBackbone=Qwen3-8b-Base, Reasoning Paradigm=Single-Turn2026.02 | 90.5 |