List your company

Tool-calling on ACEBench Extended Setting

65.17Overall ScoreGT_Funs
20.273231.929143.58555.2409Mar 12, 2026

Evaluation results

MethodLinks
GT_FunsModel Scale=Qwen2.5-7B-Instruct2026.0365.17
ToolGT (Prompting)Model Scale=Qwen2.5-7B-Instruct2026.0362.42
Tool-DC (TF)Model Scale=Qwen2.5-7B-Instruct2026.0358.83
All_FunsModel Scale=Qwen2.5-7B-Instruct2026.0358.58
HiTEC-ICLModel Scale=Qwen2.5-7B-Instruct2026.0354.67
GT_FunsModel Scale=Qwen2.5-3B-Instruct2026.0354.42
Tool-DC (TF)Model Scale=Qwen2.5-3B-Instruct2026.0348.17
GT_FunsModel Scale=Qwen2.5-1.5B-Instruct2026.0347.92
ToolGT (Prompting)Model Scale=Qwen2.5-3B-Instruct2026.0346.58
Top-KModel Scale=Qwen2.5-7B-Instruct2026.0346.31
Tool-DC (TF)Model Scale=Qwen2.5-1.5B-Instruct2026.0346.08
Top-KModel Scale=Qwen2.5-1.5B-Instruct2026.0338.58
Top-KModel Scale=Qwen2.5-3B-Instruct2026.0338.02
All_FunsModel Scale=Qwen2.5-3B-Instruct2026.0336.5
ToolGT (Prompting)Model Scale=Qwen2.5-1.5B-Instruct2026.0335.33
HiTEC-ICLModel Scale=Qwen2.5-3B-Instruct2026.0334.92
HiTEC-ICLModel Scale=Qwen2.5-1.5B-Instruct2026.0325.42
All_FunsModel Scale=Qwen2.5-1.5B-Instruct2026.0322