List your company

Function Calling on BFCL non-live (test)

82AST Accuracy (Simple Python)Ours
48.7257.366674.64Jan 25, 2026

Evaluation results

MethodLinks
OursFine-tuning dataset=Proposed Dataset2026.018282918092.985.2
ToolAceFine-tuning dataset=ToolAce2026.0178.377.5795595.477.8
APIGenFine-tuning dataset=APIGen2026.0161.572.58283.597.577.1
UntrainedStatus=Instruction tuned model baseline without specific fine-tuning2026.015048.55334.51.338.3