List your company

Tool Use on API-Bank Level 2

66.22AccuracyToolWeave-R (G)
24.058435.004245.9556.8958Apr 3, 2026

Evaluation results

MethodLinks
ToolWeave-R (G)Backbone=Llama-3.1-70B2026.0466.22
ToolWeave (O)Backbone=Llama-3.1-70B2026.0464.86
ToolWeave (G)Backbone=Phi-42026.0464.86
ToolWeave (G)Backbone=Llama-3.1-8B2026.0463.51
ToolWeave (G)Backbone=Llama-3.1-70B2026.0463.51
ToolWeave-R (G)Backbone=Phi-42026.0462.16
ToolWeave (O)Backbone=Phi-42026.0462.16
ToolWeave (O)Backbone=Llama-3.1-8B2026.0460.81
Llama-3.1-8B (Base)Backbone=Llama-3.1-8B2026.0459.46
Llama-3.1-70B (Base)Backbone=Llama-3.1-70B2026.0459.46
ToolFlowBackbone=Llama-3.1-70B2026.0459.46
ToolFlowBackbone=Phi-42026.0456.76
ToolFlowBackbone=Llama-3.1-8B2026.0454.05
ToolDialBackbone=Llama-3.1-8B2026.0452.7
ToolWeave-R (G)Backbone=Llama-3.1-8B2026.0451.35
ToolDialBackbone=Phi-42026.0444.59
ToolDialBackbone=Llama-3.1-70B2026.0440.54
Phi-4 (Base)Backbone=Phi-42026.0425.68