Tool Use on Tool Use Live
56.25Para ScoreBase
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| BaseModel Category=Base and Task Models2026.01 | 56.25 | 41.67 | |
| CURE (Coding)Model Category=Base and Task Models2026.01 | 56.25 | 37.5 | |
| ToolRL (Tool)Model Category=Base and Task Models2026.01 | 56.25 | 58.33 | |
| DARE+TIESModel Category=Merged Models2026.01 | 56.25 | 58.33 | |
| RAMModel Category=Merged Models2026.01 | 56.25 | 66.67 | |
| RAM+Model Category=Merged Models2026.01 | 56.25 | 70.83 | |
| WUDI2026.01 | 56.25 | 37.5 | |
| RAM2026.01 | 56.25 | 66.67 | |
| RAM+2026.01 | 56.25 | 70.83 | |
| DARE+TAModel Category=Merged Models2026.01 | 50 | 62.5 | |
| DARE+TA2026.01 | 50 | 62.5 | |
| TAModel Category=Merged Models2026.01 | 43.75 | 45.83 | |
| FisherModel Category=Merged Models2026.01 | 43.75 | 41.67 | |
| TIESModel Category=Merged Models2026.01 | 43.75 | 54.17 | |
| MemAgent (Memory)Model Category=Base and Task Models2026.01 | 37.5 | 50 |