Instructions following Model Ranking

See which AI models perform best on Instructions following, which ones stay reliable, and where the biggest gaps appear.

Models Shown

Average Instructions following Score

0.8

Best Model

Gemini 3.6 Flash 1.0

Failure Reasons

With failure reason Wrong answer118 With failure reason Did not follow instructions82 With failure reason API error25 With failure reason Extra formatting8 With failure reason Timed out5 With failure reason No answer2

461/461

Rank	Model	Company	Instructions following Score	Score	Total Cost	Tests Correct	Response Time (avg)
#318	GPT-5.4 none	OpenAI	0.7	0.6	$0.690	1/2	1.07s
Total Tests 2 Wrong Tests 1 Total Cost $0.690 Response Time (avg) 1.07s
#325	Kimi K2.6 none	Moonshot AI	0.7	0.5	$0.486	1/2	1.64s
Total Tests 2 Wrong Tests 1 Total Cost $0.486 Response Time (avg) 1.64s
#336	MiMo-V2.6-Flash none	Xiaomi	0.7	0.5	$0.060	1/2	810ms
Total Tests 2 Wrong Tests 1 Total Cost $0.060 Response Time (avg) 810ms
#342	Kimi K2.5 none	Moonshot AI	0.7	0.5	$0.262	1/2	2.67s
Total Tests 2 Wrong Tests 1 Total Cost $0.262 Response Time (avg) 2.67s
#353	Mistral Small 4 none	Mistral	0.7	0.5	$0.047	1/2	380ms
Total Tests 2 Wrong Tests 1 Total Cost $0.047 Response Time (avg) 380ms
#370	MiMo-V2.5 none	Xiaomi	0.7	0.5	$0.049	1/2	751ms
Total Tests 2 Wrong Tests 1 Total Cost $0.049 Response Time (avg) 751ms
#371	Qwen3.5-9B none	Qwen	0.7	0.5	$0.041	1/2	514ms
Total Tests 2 Wrong Tests 1 Total Cost $0.041 Response Time (avg) 514ms
#375	GLM 4.7 Flash none	Z.ai	0.7	0.5	$0.027	1/2	888ms
Total Tests 2 Wrong Tests 1 Total Cost $0.027 Response Time (avg) 888ms
#378	North Mini Code default	Cohere	0.7	0.5	$0.000	1/2	30.7s
Total Tests 2 Wrong Tests 1 Total Cost $0.000 Response Time (avg) 30.7s
#385	GLM 5V Turbo none	Z.ai	0.7	0.5	$0.052	1/2	1.97s
Total Tests 2 Wrong Tests 1 Total Cost $0.052 Response Time (avg) 1.97s
#388	Owl Alpha medium	Openrouter	0.7	0.5	$0.000	1/2	10.2s
Total Tests 2 Wrong Tests 1 Total Cost $0.000 Response Time (avg) 10.2s
#389	Mimo V2 PRO default	Xiaomi	0.7	0.5	$0.045	1/2	2.51s
Total Tests 2 Wrong Tests 1 Total Cost $0.045 Response Time (avg) 2.51s
#394	Mimo V2 Omni default	Xiaomi	0.7	0.4	$0.021	1/2	4.26s
Total Tests 2 Wrong Tests 1 Total Cost $0.021 Response Time (avg) 4.26s
#400	Mercury 2 none	Inception	0.7	0.4	$0.033	1/2	551ms
Total Tests 2 Wrong Tests 1 Total Cost $0.033 Response Time (avg) 551ms
#405	GLM 5 Turbo none	Z.ai	0.7	0.4	$0.047	1/2	2.13s
Total Tests 2 Wrong Tests 1 Total Cost $0.047 Response Time (avg) 2.13s

Instructions following Ranking

Filter models

Top Models by Instructions following Score

Instructions following Score vs Total Cost

Top Models by Response Time (avg)