List your company

Tool-calling on ACEBench Standard Setting

68.92Overall ScoreToolGT (Prompting)
43.54450.13256.7263.308Mar 12, 2026

Evaluation results

MethodLinks
ToolGT (Prompting)Model Scale=Qwen2.5-7B-Instruct2026.0368.92
GT_FunsModel Scale=Qwen2.5-7B-Instruct2026.0365.17
Tool-DC (TF)Model Scale=Qwen2.5-7B-Instruct2026.0364
HiTEC-ICLModel Scale=Qwen2.5-7B-Instruct2026.0361.33
All_FunsModel Scale=Qwen2.5-7B-Instruct2026.0359.92
GT_FunsModel Scale=Qwen2.5-3B-Instruct2026.0354.42
Top-KModel Scale=Qwen2.5-7B-Instruct2026.0350.83
ToolGT (Prompting)Model Scale=Qwen2.5-3B-Instruct2026.0350.5
Tool-DC (TF)Model Scale=Qwen2.5-3B-Instruct2026.0349.42
HiTEC-ICLModel Scale=Qwen2.5-3B-Instruct2026.0349.33
Tool-DC (TF)Model Scale=Qwen2.5-1.5B-Instruct2026.0349.08
GT_FunsModel Scale=Qwen2.5-1.5B-Instruct2026.0347.92
ToolGT (Prompting)Model Scale=Qwen2.5-1.5B-Instruct2026.0347.5
All_FunsModel Scale=Qwen2.5-3B-Instruct2026.0347.25
All_FunsModel Scale=Qwen2.5-1.5B-Instruct2026.0346.33
Top-KModel Scale=Qwen2.5-3B-Instruct2026.0345.78
HiTEC-ICLModel Scale=Qwen2.5-1.5B-Instruct2026.0345.17
Top-KModel Scale=Qwen2.5-1.5B-Instruct2026.0344.52