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

Function Calling on BFCL v4

68.8Score

Claude-Sonnet-4.5

Updated 13d ago

Evaluation Results

Method	Links
Claude-Sonnet-4.5 2025.12		68.8	-	-
Gemma-4-31B-it-NVFP4 2026.05		68.69	-	-
Gemma-4-31B-it 2026.05		68.6	-	-
Mix-Quant 2026.05		68.19	-	-
DeepSeek-V3.1-Nex-N1 2025.12		65.3	-	-
GLM-4.6 2025.12		62.1	-	-
GPT-5 2025.12		61.6	-	-
Qwen3-32B-Nex-N1 2025.12		60.5	-	-
Kimi-K2-thinking 2025.12		60.4	-	-
Qwen3.5-9B 2026.05		58.96	-	-
Mix-Quant 2026.05		57.89	-	-
Qwen3.5-9B-NVFP4 2026.05		56.86	-	-
DeepSeek-V3.1 2025.12		56.3	-	-
Gemini-2.5-pro 2025.12		54	-	-
Gemma-4-26B-A4B-it 2026.05		53.07	-	-
Mix-Quant 2026.05		51.94	-	-
Qwen3-30B-A3B-Nex-N1 2025.12		51.9	-	-
Gemma-4-26B-A4B-it-NVFP4 2026.05		48.13	-	-
Qwen3-32B 2025.12		45.4	-	-
InternLM3-8B-Nex-N1 2025.12		44.5	-	-
Mix-Quant 2026.05		40.63	-	-
Qwen3-8B 2026.05		40.5	-	-
Qwen3-8B-NVFP4 2026.05		38.77	-	-
Qwen3-30B-A3B 2025.12		37.5	-	-
Minimax-M2 2025.12		34.2	-	-
Qwen2.5-14B 2026.02		-	25.5	35.75
PPO 2026.02		-	44.75	56
GRPO 2026.02		-	46.25	55
GSPO 2026.02		-	50.75	56
SeeUPO 2026.02		-	55.25	57
Qwen3-14B 2026.02		-	40.25	47
PPO 2026.02		-	43.75	52
GRPO 2026.02		-	44.5	53
GSPO 2026.02		-	45.75	55
SeeUPO 2026.02		-	58	65