Instructions following Model Ranking

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

Models Shown

Average Instructions following Score

8.6

Best Model

Kimi K2.5 10.0

Failure Reasons

With failure reason Wrong answer61 With failure reason Did not follow instructions19 With failure reason Extra formatting3 With failure reason No answer2 With failure reason API error1 With failure reason Timed out1

216/216

Rank	Model	Company	Instructions following Score	Score	Total Cost	Tests Correct	Response Time (avg)
#148	Qwen3.5-122B-A10B none	Qwen	6.3	5.7	$0.247	1/2	513ms
Total Tests 2 Wrong Tests 1 Total Cost $0.247 Response Time (avg) 513ms
#203	Grok 4.20 none	X AI	6.3	4.1	$0.057	1/2	445ms
Total Tests 2 Wrong Tests 1 Total Cost $0.057 Response Time (avg) 445ms
#211	Laguna Xs.2 none	Poolside	6.5	3.8	$0.004	1/2	439ms
Total Tests 2 Wrong Tests 1 Total Cost $0.004 Response Time (avg) 439ms
#171	Mistral Small 4 none	Mistral	6.5	5.1	$0.022	1/2	380ms
Total Tests 2 Wrong Tests 1 Total Cost $0.022 Response Time (avg) 380ms
#166	Laguna XS 2.1 none	Poolside	3.8	5.3	$0.008	0/2	364ms
Total Tests 2 Wrong Tests 2 Total Cost $0.008 Response Time (avg) 364ms
#207	Granite 4.1 8B none	IBM Granite	3.6	4.0	$0.007	0/2	344ms
Total Tests 2 Wrong Tests 2 Total Cost $0.007 Response Time (avg) 344ms

Instructions following Ranking

Filter models

Top Models by Instructions following Score

Instructions following Score vs Total Cost

Top Models by Response Time (avg)