Tool Calling Model Ranking

AI BENCHY Category

See which AI models perform best on Tool Calling, which ones stay reliable, and where the biggest gaps appear. Sort by: Response Time (avg) ↑.

Models Shown

Average Tool Calling Score

8.7

Best Model

Failure Reasons

With failure reason API error15 With failure reason Invalid tool call7 With failure reason Did not follow instructions6 With failure reason No answer2 With failure reason Wrong answer2

Rank	Model	Company	Tool Calling Score	Score	Tests Correct	Response Time (avg)
#154	Qwen3.5-9B none	Qwen	10.0	4.6	1/1	1.27s
#142	Mistral Small 4 none	Mistral	10.0	4.9	1/1	1.40s
#81	Mercury 2 medium	Inception	10.0	6.6	1/1	1.89s
#97	Gemini 2.5 Flash none	Google	10.0	6.2	1/1	1.91s
#146	Laguna Xs.2 none	Poolside	3.0	4.8	0/1	1.93s
#131	Qwen3.5-122B-A10B none	Qwen	10.0	5.3	1/1	2.04s
#163	Granite 4.1 8B none	IBM Granite	10.0	4.0	1/1	2.17s
#152	MiMo-V2-Flash none	Xiaomi	10.0	4.6	1/1	2.28s
#117	Qwen3.5-35B-A3B none	Qwen	10.0	5.6	1/1	2.30s
#144	GPT-5.4 Mini none	OpenAI	3.0	4.9	0/1	2.32s
#143	MiMo-V2.5 none	Xiaomi	10.0	4.9	1/1	2.43s
#140	Qwen3 Coder Next none	Qwen	10.0	4.9	1/1	2.47s
#128	Qwen3.6 Flash none	Qwen	10.0	5.4	1/1	2.49s
#147	GPT-4o-mini none	OpenAI	10.0	4.8	1/1	2.51s
#150	Qwen3 Coder Next medium	Qwen	10.0	4.6	1/1	2.64s

Tool Calling Ranking