List your company

Tool-augmented reasoning on BFCL Multi-Turn v3

69.1Overall ScoreAPIGen-MT
6.90823.05439.255.346Jan 6, 2026

Evaluation results

MethodLinks
APIGen-MTBase Model=Llama3.1-8B-Inst2026.0169.17769.56367
GPT-4o-2024-11-202026.01506145.535.558
ToolACE-MT-8BBase Model=Llama3.1-8B-Inst2026.0140.357.531.53438
Qwen3-8B2026.013742.538.531.535.5
Gemini-2.5-Pro-Preview-05-062026.0134.639.529.531.538
MASBase Model=Llama3.1-8B-Inst2026.0131.446.5193129
DeepSeek-V3-03242026.0129.941212334.5
DiGiT-TCBase Model=Llama3.1-8B-Inst2026.012742161733
MagnetBase Model=Qwen-Coder-7B-Inst2026.0126.535.52427.519
ToolWeaveBase Model=Llama3.1-8B-Inst2026.012531.520.524.523.5
ToucanBase Model=Qwen2.5-7B-Inst2026.0122.6————
Mistral-Small-25062026.0117.622.511.51917.5
Llama3.1-70B-Inst2026.0112.5171310.59.5
Llama3.1-8B-Inst2026.019.3121078