Share your thoughts, 1 month free Claude Pro on usSee more

Tool Use on BFCL

94Accuracy

Official Instruct Model

Updated 1d ago

Evaluation Results

Method	Links
Official Instruct Model 2026.05		94
Opus-4.7 (xHigh) 2026.05		91.33
GLM-4.7 & ANDES 2026.05		89
Opus-4.6 (1M) 2026.05		87.33
Gemini-3.1-Pro 2026.05		85.67
Qwen3-4B 2026.05		68.5
Qwen3-8B 2026.05		68.5
Qwen 3 VL 32B Instruct 2025.12		66.3
Qwen 3 VL 8B Inst 2025.12		66.2
GPT-5 nano 2026.05		64.4
Qwen 3 32B 2025.12		63.1
Qwen 2.5 32B 2025.12		62.8
Ministral-3-8B 2026.05		62
Qwen 3 8B 2025.12		60.2
Olmo 3.1 32B Instruct 2025.12		58.8
Olmo 3.1 32B Instruct 2025.12		58.6
gemma-3-12b-it 2026.05		58.2
Olmo 3.1 32B Instruct 2025.12		57
Qwen 2.5 7B 2025.12		55.8
gpt-oss-20b 2026.05		54.6
Llama-3.1-8B 2026.05		54.2
Olmo 3 7B Instruct 2025.12		49.8
Olmo 3 7B Instruct 2025.12		49.6
EngGPT2-16B-A3B 2026.05		49.1
Olmo 3 7B Instruct 2025.12		48.9
Llama-3.2-3B 2026.05		45.3
gemma-3-4b-it 2026.05		43.2
GLM-4.7 (Scaffold-only) 2026.05		43
LLaMAntino-3-8B 2026.05		38.3
GPT-5.2 2026.05		29.33
Opus-4.6 2026.05		28.33
Moonlight-16B-A3B 2026.05		26.3
Velvet-14B 2026.05		25.7
Minerva-7B 2026.05		25
FastwebMIIA-7B 2026.05		24.5
deepseek-moe-16b 2026.05		22.5
Base Model (Qwen3-1.7B) 2026.05		0
Sonnet-4.5 2026.05		0
MiniMax-M2.5 2026.05		0
MiniMax-M2.1 2026.05		0
Qwen3-Max 2026.05		0
Kimi-K2-Thinking 2026.05		0
GPT-5.1-Codex-Max 2026.05		0
GPT-5.4 (High) 2026.05		0
GLM-4.7 (OpenCode) 2026.05		0