List your company

Function Calling on BFCL (FN/SF Metrics)

0False Negative RateMPMA DPMA
-4235077Apr 22, 2026

Evaluation results

MethodLinks
MPMA DPMAModel=Qwen3-1.7B, Thinking Mode=Base2026.0400
MPMA DPMAModel=Qwen3-8B, Thinking Mode=Think2026.0400
MPMA DPMAModel=Qwen3-14B, Thinking Mode=Think2026.0400
MPMA GAPMAModel=Qwen3-1.7B, Thinking Mode=Base2026.0400
MPMA GAPMAModel=Qwen3-1.7B, Thinking Mode=Think2026.0400
MPMA GAPMAModel=Qwen3-8B, Thinking Mode=Think2026.0400
MPMA BenignModel=Llama-3B2026.0411
MPMA BenignModel=Qwen3-1.7B, Thinking Mode=Base2026.0411
MPMA BenignModel=Qwen3-1.7B, Thinking Mode=Think2026.0411
MPMA BenignModel=Qwen3-8B, Thinking Mode=Think2026.0411
MPMA BenignModel=Qwen3-14B, Thinking Mode=Think2026.0411
MPMA DPMAModel=Llama-3B2026.0411
MPMA DPMAModel=Qwen3-1.7B, Thinking Mode=Think2026.0411
MPMA DPMAModel=Qwen3-14B, Thinking Mode=Base2026.0411
MPMA GAPMAModel=Llama-3B2026.0411
MPMA GAPMAModel=Qwen3-14B, Thinking Mode=Think2026.0411
MPMA BenignModel=Qwen3-8B, Thinking Mode=Base2026.0422
MPMA BenignModel=Qwen3-14B, Thinking Mode=Base2026.0422
MPMA DPMAModel=Qwen3-8B, Thinking Mode=Base2026.0422
MPMA GAPMAModel=Qwen3-8B, Thinking Mode=Base2026.0422
MPMA GAPMAModel=Qwen3-14B, Thinking Mode=Base2026.0422
MPMA BenignModel=Mistral-7B2026.0477
MPMA GAPMAModel=Mistral-7B2026.0499
MPMA DPMAModel=Mistral-7B2026.041010
Function Injection (FS)Model=Mistral-7B2026.044847
Function Injection (FS)Model=Qwen3-1.7B, Thinking Mode=Think2026.045049
Function Injection (FS)Model=Llama-3B2026.045757
Function Injection (FS)Model=Qwen3-1.7B, Thinking Mode=Base2026.046464
Function Injection (FS)Model=Qwen3-8B, Thinking Mode=Base2026.046464
Function Injection (FS)Model=Qwen3-8B, Thinking Mode=Think2026.046564
Function Injection (FS)Model=Qwen3-14B, Thinking Mode=Base2026.046867
Function Injection (FS)Model=Qwen3-14B, Thinking Mode=Think2026.046866
FHAModel=Qwen3-8B, Thinking Mode=Base2026.047065
FHAModel=Qwen3-8B, Thinking Mode=Think2026.047065
Function Injection (ZS)Model=Mistral-7B2026.047956
Function Injection (ZS)Model=Qwen3-14B, Thinking Mode=Think2026.047947
Function Injection (ZS)Model=Llama-3B2026.048059
Function Injection (ZS)Model=Qwen3-1.7B, Thinking Mode=Think2026.048151
Function Injection (ZS)Model=Qwen3-8B, Thinking Mode=Think2026.048147
FHAModel=Qwen3-14B, Thinking Mode=Base2026.048273
FHAModel=Qwen3-14B, Thinking Mode=Think2026.048273
Function Injection (ZS)Model=Qwen3-8B, Thinking Mode=Base2026.048655
Standard InferenceModel=Llama-3B2026.048888
Function Injection (ZS)Model=Qwen3-1.7B, Thinking Mode=Base2026.049158
Function Injection (ZS)Model=Qwen3-14B, Thinking Mode=Base2026.049157
Standard InferenceModel=Mistral-7B2026.049696
Standard InferenceModel=Qwen3-1.7B, Thinking Mode=Base2026.049696
Standard InferenceModel=Qwen3-1.7B, Thinking Mode=Think2026.049797
Standard InferenceModel=Qwen3-8B, Thinking Mode=Base2026.049797
FHAModel=Llama-3B2026.049788
Standard InferenceModel=Qwen3-14B, Thinking Mode=Base2026.049898
Standard InferenceModel=Qwen3-14B, Thinking Mode=Think2026.049999
FHAModel=Mistral-7B2026.049992
Standard InferenceModel=Qwen3-8B, Thinking Mode=Think2026.04100100
FHAModel=Qwen3-1.7B, Thinking Mode=Base2026.0410092
FHAModel=Qwen3-1.7B, Thinking Mode=Think2026.0410092