Tool-Integrated Reasoning on Overall 9 Benchmarks
88Average ScoreAutoTraj
Evaluation Results
| Method | Links | |
|---|---|---|
| AutoTrajCategory=SFT-RL TIR Methods2026.01 | 88 | |
| AutoTIRCategory=RL-only TIR Methods2026.01 | 83 | |
| Tool-Star-SFTCategory=SFT-only TIR Methods2026.01 | 82 | |
| Tool-StarCategory=SFT-RL TIR Methods2026.01 | 79 | |
| R1-SearcherCategory=RL-only TIR Methods2026.01 | 78 | |
| Vanilla SFT-RL TIRCategory=SFT-RL TIR Methods2026.01 | 78 | |
| Qwen2.5-7B-InstructFramework=Multi-Dimensional Trajectory Evaluation2026.01 | 75 | |
| ToRLCategory=RL-only TIR Methods2026.01 | 74 | |
| ReSearchCategory=RL-only TIR Methods2026.01 | 68 |