Mathematical Reasoning on Olympiad (Avg@16, Pass@16)
47.64Average Score @16TAO-RL
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| TAO-RLBase Model=Qwen3-4B-Base2026.06 | 47.64 | 73.2 | |
| SimpleTIRBase Model=Qwen3-4B-Base2026.06 | 46.71 | 72.8 | |
| SimpleTIRBase Model=Qwen2.5-1.5B2026.06 | 30.48 | 57 | |
| TAO-RLBase Model=Qwen2.5-1.5B2026.06 | 30.21 | 58 | |
| Base modelBase Model=Qwen3-4B-Base2026.06 | 22.54 | 65.4 | |
| Base modelBase Model=Qwen2.5-1.5B2026.06 | 1.48 | 15.4 |