Tool Use on API-Bank Level 2
66.22AccuracyToolWeave-R (G)
Evaluation Results
| Method | Links | |
|---|---|---|
| ToolWeave-R (G)Backbone=Llama-3.1-70B2026.04 | 66.22 | |
| ToolWeave (O)Backbone=Llama-3.1-70B2026.04 | 64.86 | |
| ToolWeave (G)Backbone=Phi-42026.04 | 64.86 | |
| ToolWeave (G)Backbone=Llama-3.1-8B2026.04 | 63.51 | |
| ToolWeave (G)Backbone=Llama-3.1-70B2026.04 | 63.51 | |
| ToolWeave-R (G)Backbone=Phi-42026.04 | 62.16 | |
| ToolWeave (O)Backbone=Phi-42026.04 | 62.16 | |
| ToolWeave (O)Backbone=Llama-3.1-8B2026.04 | 60.81 | |
| Llama-3.1-8B (Base)Backbone=Llama-3.1-8B2026.04 | 59.46 | |
| Llama-3.1-70B (Base)Backbone=Llama-3.1-70B2026.04 | 59.46 | |
| ToolFlowBackbone=Llama-3.1-70B2026.04 | 59.46 | |
| ToolFlowBackbone=Phi-42026.04 | 56.76 | |
| ToolFlowBackbone=Llama-3.1-8B2026.04 | 54.05 | |
| ToolDialBackbone=Llama-3.1-8B2026.04 | 52.7 | |
| ToolWeave-R (G)Backbone=Llama-3.1-8B2026.04 | 51.35 | |
| ToolDialBackbone=Phi-42026.04 | 44.59 | |
| ToolDialBackbone=Llama-3.1-70B2026.04 | 40.54 | |
| Phi-4 (Base)Backbone=Phi-42026.04 | 25.68 |