List your company

Tool-calling on BFCL Standard Setting

86.46Non-Live AccuracyAll_Funs
64.443270.159175.87581.5909Mar 12, 2026

Evaluation results

MethodLinks
All_FunsModel Scale=Qwen2.5-7B-Instruct2026.0386.4667.4476.95
GT_FunsModel Scale=Qwen2.5-7B-Instruct2026.0385.8178.0281.92
HiTEC-ICLModel Scale=Qwen2.5-7B-Instruct2026.0384.9876.2480.61
Tool-DC (TF)Model Scale=Qwen2.5-7B-Instruct2026.0384.7374.8379.78
Top-KModel Scale=Qwen2.5-7B-Instruct2026.0384.675.580.05
GT_FunsModel Scale=Qwen2.5-3B-Instruct2026.0379.2369.1374.18
HiTEC-ICLModel Scale=Qwen2.5-3B-Instruct2026.0378.963.871.35
Tool-DC (TF)Model Scale=Qwen2.5-3B-Instruct2026.0378.5466.6272.58
All_FunsModel Scale=Qwen2.5-3B-Instruct2026.0378.0863.5170.8
Top-KModel Scale=Qwen2.5-3B-Instruct2026.037866.0372.02
ToolGT (Prompting)Model Scale=Qwen2.5-7B-Instruct2026.0377.7368.0272.88
Tool-DC (TF)Model Scale=Qwen2.5-1.5B-Instruct2026.0377.6363.4370.53
Top-KModel Scale=Qwen2.5-1.5B-Instruct2026.0376.3563.870.08
HiTEC-ICLModel Scale=Qwen2.5-1.5B-Instruct2026.0375.5661.5168.54
GT_FunsModel Scale=Qwen2.5-1.5B-Instruct2026.0370.9662.7766.87
All_FunsModel Scale=Qwen2.5-1.5B-Instruct2026.0369.9658.1864.07
ToolGT (Prompting)Model Scale=Qwen2.5-3B-Instruct2026.0368.9457.2263.08
ToolGT (Prompting)Model Scale=Qwen2.5-1.5B-Instruct2026.0365.2952.2658.78