Mathematical Reasoning on AIME25 (Average Score)
0.84Average ScoreTool-Star
Evaluation Results
| Method | Links | |
|---|---|---|
| Tool-StarCategory=SFT-RL TIR Methods2026.01 | 0.84 | |
| Tool-Star-SFTCategory=SFT-only TIR Methods2026.01 | 0.82 | |
| ToRLCategory=RL-only TIR Methods2026.01 | 0.79 | |
| Vanilla SFT-RL TIRCategory=SFT-RL TIR Methods2026.01 | 0.78 | |
| AutoTrajCategory=SFT-RL TIR Methods2026.01 | 0.76 | |
| AutoTIRCategory=RL-only TIR Methods2026.01 | 0.67 | |
| ReSearchCategory=RL-only TIR Methods2026.01 | 0.37 | |
| Qwen2.5-7B-InstructFramework=Multi-Dimensional Trajectory Evaluation2026.01 | 0 | |
| R1-SearcherCategory=RL-only TIR Methods2026.01 | 0 |