Our new X account is live! Follow @wizwand_team for updates

Function Calling on Berkeley Function Call Leaderboard (BFCL) Live (Out-of-Domain)

0.876AST Simple

Qwen3-4B

Updated 4d ago

Evaluation Results

Method	Links
Qwen3-4B 2026.02		0.876	0.8	0.75	0.833	0.833
Qwen3-8B 2026.02		0.849	0.794	0.625	0.75	0.834
GPT-4-turbo 2026.02		0.837	0.786	0.812	0.708	0.81
GPT-4o 2026.02		0.814	0.788	0.875	0.75	0.826
Qwen2.5-32B-Instruct 2026.02		0.802	0.801	0.438	0.625	0.822
GPT-4o-mini 2026.02		0.787	0.762	0.875	0.708	0.799
BigAgent-8B 2026.02		0.779	0.774	0.875	0.708	0.816
Qwen2.5-14B-Instruct 2026.02		0.771	0.75	0.75	0.708	0.79
Hammer2.1-7B 2026.02		0.767	0.774	0.812	0.708	0.816
Qwen3-1.7B 2026.02		0.756	0.727	0.75	0.75	0.769
Qwen2.5-7B-Instruct 2026.02		0.756	0.756	0.688	0.667	0.796
HyFunc♣ 2026.02		0.752	0.755	0.75	0.708	0.801
xLAM-8x7B-r 2026.02		0.748	0.793	0.438	0.583	0.743
HyFunc♥ 2026.02		0.748	0.752	0.688	0.667	0.786
Qwen2.5-3B-Instruct 2026.02		0.74	0.721	0.625	0.458	0.749
Qwen2.5-1.5B-Instruct 2026.02		0.74	0.661	0.5	0.458	0.727
ToolACE-8B 2026.02		0.733	0.767	0.812	0.708	0.81
Hammer2.1-3B 2026.02		0.733	0.733	0.625	0.667	0.79
GLM4-9B-chat 2026.02		0.725	0.644	0	0	0.551
xLAM-7B-r 2026.02		0.721	0.749	0.5	0.625	0.766
Hammer2.1-1.5B 2026.02		0.713	0.698	0.5	0.625	0.755
Granite-20B 2026.02		0.682	0.563	0.438	0.583	0.786
Qwen3-0.6B 2026.02		0.659	0.544	0.375	0.542	0.622
xLAM-1B-r 2026.02		0.64	0.534	0.062	0	0.512
Hammer2.1-0.5B 2026.02		0.601	0.58	0.5	0.458	0.635
Qwen2.5-0.5B-Instruct 2026.02		0.562	0.413	0.562	0.208	0.524