Tool Use on Tool Use Non-Live
0.925ParaDARE+TA
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| DARE+TAModel Category=Merged Models2026.01 | 0.925 | 0.895 | |
| DARE+TA2026.01 | 0.925 | 0.895 | |
| DARE+TIESModel Category=Merged Models2026.01 | 0.915 | 0.9 | |
| ToolRL (Tool)Model Category=Base and Task Models2026.01 | 0.91 | 0.89 | |
| RAMModel Category=Merged Models2026.01 | 0.91 | 0.915 | |
| RAM2026.01 | 0.91 | 0.915 | |
| RAM+Model Category=Merged Models2026.01 | 0.905 | 0.91 | |
| RAM+2026.01 | 0.905 | 0.91 | |
| WUDI2026.01 | 0.89 | 0.91 | |
| TAModel Category=Merged Models2026.01 | 0.875 | 0.695 | |
| FisherModel Category=Merged Models2026.01 | 0.865 | 0.635 | |
| TIESModel Category=Merged Models2026.01 | 0.84 | 0.675 | |
| MemAgent (Memory)Model Category=Base and Task Models2026.01 | 0.785 | 0.485 | |
| BaseModel Category=Base and Task Models2026.01 | 0.68 | 0.55 | |
| CURE (Coding)Model Category=Base and Task Models2026.01 | 0.64 | 0.515 |