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

8.6

Best Model

Gemini 3 Flash Preview 10.0

Failure Reasons

With failure reason Wrong answer57 With failure reason Did not follow instructions18 With failure reason Extra formatting3 With failure reason No answer2 With failure reason API error1 With failure reason Timed out1

206/206

Rank	Model	Company	Instructions following Score	Score	Total Cost	Tests Correct	Response Time (avg)
#1	Gemini 3 Flash Preview medium	Google	10.0	9.6	$0.742	2/2	4.04s
Total Tests 2 Wrong Tests 0 Total Cost $0.742 Response Time (avg) 4.04s
#2	Gemini 3.5 Flash high	Google	10.0	9.5	$1.976	2/2	3.35s
Total Tests 2 Wrong Tests 0 Total Cost $1.976 Response Time (avg) 3.35s
#3	GPT-5.6 Sol low	OpenAI	10.0	9.5	$0.971	2/2	2.27s
Total Tests 2 Wrong Tests 0 Total Cost $0.971 Response Time (avg) 2.27s
#4	GPT-5.6 Sol medium	OpenAI	10.0	9.4	$1.316	2/2	2.50s
Total Tests 2 Wrong Tests 0 Total Cost $1.316 Response Time (avg) 2.50s
#5	GPT-5.6 Sol high	OpenAI	10.0	9.4	$1.234	2/2	2.73s
Total Tests 2 Wrong Tests 0 Total Cost $1.234 Response Time (avg) 2.73s
#7	Gemini 3.1 Pro Preview medium	Google	10.0	9.2	$1.361	2/2	9.56s
Total Tests 2 Wrong Tests 0 Total Cost $1.361 Response Time (avg) 9.56s
#8	Qwen3.7 Max medium	Qwen	10.0	9.2	$1.116	2/2	7.46s
Total Tests 2 Wrong Tests 0 Total Cost $1.116 Response Time (avg) 7.46s
#10	GPT-5.5 medium	OpenAI	10.0	9.0	$4.137	2/2	3.36s
Total Tests 2 Wrong Tests 0 Total Cost $4.137 Response Time (avg) 3.36s
#13	GPT-5.3-Codex medium	OpenAI	10.0	8.9	$0.920	2/2	3.04s
Total Tests 2 Wrong Tests 0 Total Cost $0.920 Response Time (avg) 3.04s
#14	Claude Opus 4.8 medium	Anthropic	10.0	8.8	$1.931	2/2	3.32s
Total Tests 2 Wrong Tests 0 Total Cost $1.931 Response Time (avg) 3.32s
#15	Claude Opus 4.7 medium	Anthropic	10.0	8.7	$1.477	2/2	1.57s
Total Tests 2 Wrong Tests 0 Total Cost $1.477 Response Time (avg) 1.57s
#17	Claude Fable 5 medium	Anthropic	10.0	8.6	$3.478	2/2	5.90s
Total Tests 2 Wrong Tests 0 Total Cost $3.478 Response Time (avg) 5.90s
#18	GPT-5.4 medium	OpenAI	10.0	8.5	$1.533	2/2	3.11s
Total Tests 2 Wrong Tests 0 Total Cost $1.533 Response Time (avg) 3.11s
#19	Qwen3.6 Max Preview medium	Qwen	10.0	8.4	$1.143	2/2	24.3s
Total Tests 2 Wrong Tests 0 Total Cost $1.143 Response Time (avg) 24.3s
#26	GPT-5 Mini medium	OpenAI	10.0	8.1	$0.237	2/2	11.6s
Total Tests 2 Wrong Tests 0 Total Cost $0.237 Response Time (avg) 11.6s

Instructions following Ranking

Filter models

Top Models by Instructions following Score

Instructions following Score vs Total Cost

Top Models by Response Time (avg)