List your company

Tool-calling on BFCL Extended Setting

85.81Non-Live ScoreGT_Funs
37.730850.212962.69575.1771Mar 12, 2026

Evaluation results

MethodLinks
GT_FunsModel Scale=Qwen2.5-7B-Instruct2026.0385.8178.0281.92
Tool-DC (TF)Model Scale=Qwen2.5-7B-Instruct2026.0384.47077.2
GT_FunsModel Scale=Qwen2.5-3B-Instruct2026.0379.2369.1374.18
HiTEC-ICLModel Scale=Qwen2.5-7B-Instruct2026.0376.8165.1470.98
ToolGT (Prompting)Model Scale=Qwen2.5-7B-Instruct2026.037660.5568.28
All_FunsModel Scale=Qwen2.5-7B-Instruct2026.0375.7162.7769.24
Tool-DC (TF)Model Scale=Qwen2.5-3B-Instruct2026.0371.7957.7464.77
GT_FunsModel Scale=Qwen2.5-1.5B-Instruct2026.0370.9662.7766.87
Top-KModel Scale=Qwen2.5-7B-Instruct2026.0370.2354.1862.21
Tool-DC (TF)Model Scale=Qwen2.5-1.5B-Instruct2026.0364.136263.07
HiTEC-ICLModel Scale=Qwen2.5-3B-Instruct2026.0363.7945.2354.51
Top-KModel Scale=Qwen2.5-3B-Instruct2026.0363.7346.7155.22
All_FunsModel Scale=Qwen2.5-3B-Instruct2026.0362.7344.3453.54
Top-KModel Scale=Qwen2.5-1.5B-Instruct2026.0360.3143.651.96
ToolGT (Prompting)Model Scale=Qwen2.5-3B-Instruct2026.0359.2954.9257.11
HiTEC-ICLModel Scale=Qwen2.5-1.5B-Instruct2026.0346.4639.9743.22
All_FunsModel Scale=Qwen2.5-1.5B-Instruct2026.0340.6933.2336.96
ToolGT (Prompting)Model Scale=Qwen2.5-1.5B-Instruct2026.0339.5835.8337.71