Tool Calling Model Ranking

See which AI models perform best on Tool Calling, which ones stay reliable, and where the biggest gaps appear. Sort by: Tests Correct ↑.

Models Shown

Average Tool Calling Score

8.8

Best Model

Failure Reasons

With failure reason API error17 With failure reason Invalid tool call9 With failure reason Did not follow instructions8 With failure reason Wrong answer3 With failure reason No answer2

216/216

Rank	Model	Company	Tool Calling Score	Score	Total Cost	Tests Correct	Response Time (avg)
#202	Hunter Alpha none	OpenRouter	10.0	4.2	$0.000	1/1	6.02s
Total Tests 1 Wrong Tests 0 Total Cost $0.000 Response Time (avg) 6.02s
#203	Grok 4.20 none	X AI	10.0	4.1	$0.057	1/1	4.63s
Total Tests 1 Wrong Tests 0 Total Cost $0.057 Response Time (avg) 4.63s
#205	Hy3 preview none	Tencent	10.0	4.0	$0.003	1/1	33.8s
Total Tests 1 Wrong Tests 0 Total Cost $0.003 Response Time (avg) 33.8s
#206	MiMo-V2-Flash none	Xiaomi	10.0	4.0	$0.025	1/1	2.28s
Total Tests 1 Wrong Tests 0 Total Cost $0.025 Response Time (avg) 2.28s
#207	Granite 4.1 8B none	IBM Granite	10.0	4.0	$0.007	1/1	2.17s
Total Tests 1 Wrong Tests 0 Total Cost $0.007 Response Time (avg) 2.17s
#210	Qwen3.5-9B medium	Qwen	10.0	3.8	$0.036	1/1	4.31s
Total Tests 1 Wrong Tests 0 Total Cost $0.036 Response Time (avg) 4.31s

Tool Calling Ranking