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: Total Cost ↑.

Models Shown

Average Instructions following Score

8.6

Best Model

North Mini Code 9.8

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)
#49	DeepSeek V4 Flash high	DeepSeek	10.0	7.7	$0.041	2/2	15.4s
Total Tests 2 Wrong Tests 0 Total Cost $0.041 Response Time (avg) 15.4s
#147	GLM 5 none	Z.ai	10.0	5.7	$0.041	2/2	1.48s
Total Tests 2 Wrong Tests 0 Total Cost $0.041 Response Time (avg) 1.48s
#186	GPT-5.4 Nano none	OpenAI	6.3	4.8	$0.041	1/2	784ms
Total Tests 2 Wrong Tests 1 Total Cost $0.041 Response Time (avg) 784ms
#164	KAT-Coder-Air V2.5 low	Kwaipilot	9.8	5.4	$0.041	2/2	1.64s
Total Tests 2 Wrong Tests 0 Total Cost $0.041 Response Time (avg) 1.64s
#156	DeepSeek V4 Flash none	DeepSeek	6.5	5.6	$0.042	1/2	17.5s
Total Tests 2 Wrong Tests 1 Total Cost $0.042 Response Time (avg) 17.5s
#119	MiMo-V2-Flash medium	Xiaomi	10.0	6.3	$0.043	2/2	4.28s
Total Tests 2 Wrong Tests 0 Total Cost $0.043 Response Time (avg) 4.28s
#117	LongCat 2.0 none	Meituan	6.5	6.3	$0.044	1/2	2.82s
Total Tests 2 Wrong Tests 1 Total Cost $0.044 Response Time (avg) 2.82s
#153	Mimo V2 PRO none	Xiaomi	6.5	5.6	$0.045	1/2	2.51s
Total Tests 2 Wrong Tests 1 Total Cost $0.045 Response Time (avg) 2.51s
#128	Gemini 3.1 Flash Lite none	Google	10.0	6.1	$0.046	2/2	859ms
Total Tests 2 Wrong Tests 0 Total Cost $0.046 Response Time (avg) 859ms
#176	GLM 5 Turbo none	Z.ai	6.5	5.1	$0.047	1/2	2.13s
Total Tests 2 Wrong Tests 1 Total Cost $0.047 Response Time (avg) 2.13s
#126	Gemini 3.1 Flash Lite minimal	Google	10.0	6.1	$0.047	2/2	932ms
Total Tests 2 Wrong Tests 0 Total Cost $0.047 Response Time (avg) 932ms
#141	Hy3 preview high	Tencent	10.0	5.9	$0.048	2/2	34.4s
Total Tests 2 Wrong Tests 0 Total Cost $0.048 Response Time (avg) 34.4s
#155	KAT-Coder-Air V2.5 medium	Kwaipilot	10.0	5.6	$0.048	2/2	1.50s
Total Tests 2 Wrong Tests 0 Total Cost $0.048 Response Time (avg) 1.50s
#151	GLM 5V Turbo none	Z.ai	6.5	5.6	$0.052	1/2	1.97s
Total Tests 2 Wrong Tests 1 Total Cost $0.052 Response Time (avg) 1.97s
#112	Gemini 3.1 Flash Lite Preview none	Google	10.0	6.4	$0.052	2/2	1.13s
Total Tests 2 Wrong Tests 0 Total Cost $0.052 Response Time (avg) 1.13s

Instructions following Ranking

Filter models

Top Models by Instructions following Score

Instructions following Score vs Total Cost

Top Models by Response Time (avg)