Tool Use on CONFETTI
45.45AccuracyToolWeave (O)
Evaluation Results
| Method | Links | |
|---|---|---|
| ToolWeave (O)Backbone=Llama-3.1-70B2026.04 | 45.45 | |
| ToolWeave (O)Backbone=Llama-3.1-8B2026.04 | 36.76 | |
| ToolWeave (G)Backbone=Llama-3.1-70B2026.04 | 34.78 | |
| ToolWeave-R (G)Backbone=Llama-3.1-70B2026.04 | 33.99 | |
| ToolWeave (O)Backbone=Phi-42026.04 | 33.6 | |
| Llama-3.1-70B (Base)Backbone=Llama-3.1-70B2026.04 | 33 | |
| ToolWeave-R (G)Backbone=Phi-42026.04 | 32.41 | |
| ToolWeave (G)Backbone=Phi-42026.04 | 31.42 | |
| ToolWeave (G)Backbone=Llama-3.1-8B2026.04 | 28.85 | |
| ToolFlowBackbone=Llama-3.1-70B2026.04 | 28.46 | |
| ToolDialBackbone=Llama-3.1-8B2026.04 | 23.12 | |
| Llama-3.1-8B (Base)Backbone=Llama-3.1-8B2026.04 | 20.55 | |
| ToolWeave-R (G)Backbone=Llama-3.1-8B2026.04 | 19.37 | |
| ToolFlowBackbone=Llama-3.1-8B2026.04 | 17.39 | |
| ToolFlowBackbone=Phi-42026.04 | 15.61 | |
| ToolDialBackbone=Phi-42026.04 | 13.64 | |
| Phi-4 (Base)Backbone=Phi-42026.04 | 13.44 | |
| ToolDialBackbone=Llama-3.1-70B2026.04 | 11.46 |