Single-Turn Mathematical Reasoning on AMC 23
85.08Peak avg@32 ScoreOTB
Evaluation Results
| Method | Links | |
|---|---|---|
| OTBBackbone=Qwen3-8b-Base, Reasoning Paradigm=Single-Turn2026.02 | 85.08 | |
| OPOBackbone=Qwen3-8b-Base, Reasoning Paradigm=Single-Turn2026.02 | 84.53 | |
| GRPOBackbone=Qwen3-8b-Base, Reasoning Paradigm=Single-Turn2026.02 | 80.86 | |
| OGBBackbone=Qwen3-8b-Base, Reasoning Paradigm=Single-Turn2026.02 | 80.55 | |
| RLOOBackbone=Qwen3-8b-Base, Reasoning Paradigm=Single-Turn2026.02 | 74.53 |