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

0.8

Best Model

Ling 3.1 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)
#165	Grok 4.7 low	X AI	0.8	0.7	$1.933	1/2	6.19s
Total Tests 2 Wrong Tests 1 Total Cost $1.933 Response Time (avg) 6.19s
#60	Muse Spark 1.2 high	Meta	1.0	0.9	$2.018	2/2	5.43s
Total Tests 2 Wrong Tests 0 Total Cost $2.018 Response Time (avg) 5.43s
#76	Seed 2.1 Turbo medium	Bytedance Seed	1.0	0.9	$2.042	2/2	7.48s
Total Tests 2 Wrong Tests 0 Total Cost $2.042 Response Time (avg) 7.48s
#384	Gemini 3.1 Flash Lite high	Google	0.7	0.5	$2.044	1/2	23.3s
Total Tests 2 Wrong Tests 1 Total Cost $2.044 Response Time (avg) 23.3s
#50	Muse Spark Open xhigh	Meta	1.0	0.9	$2.081	2/2	23.5s
Total Tests 2 Wrong Tests 0 Total Cost $2.081 Response Time (avg) 23.5s
#251	Claude Sonnet 4.6 medium	Anthropic	1.0	0.6	$2.126	2/2	2.61s
Total Tests 2 Wrong Tests 0 Total Cost $2.126 Response Time (avg) 2.61s
#28	Claude Opus 5.5 high	Anthropic	1.0	0.9	$2.133	2/2	21.3s
Total Tests 2 Wrong Tests 0 Total Cost $2.133 Response Time (avg) 21.3s
#14	GPT-6 Astra low	OpenAI	1.0	1.0	$2.160	2/2	2.65s
Total Tests 2 Wrong Tests 0 Total Cost $2.160 Response Time (avg) 2.65s
#27	GPT-6.1 Terra max	OpenAI	0.9	0.9	$2.209	1/2	4.20s
Total Tests 2 Wrong Tests 1 Total Cost $2.209 Response Time (avg) 4.20s
#67	GPT-5.4 medium	OpenAI	1.0	0.9	$2.213	2/2	3.11s
Total Tests 2 Wrong Tests 0 Total Cost $2.213 Response Time (avg) 3.11s
#139	Grok 4.6 medium	X AI	1.0	0.8	$2.270	2/2	12.8s
Total Tests 2 Wrong Tests 0 Total Cost $2.270 Response Time (avg) 12.8s
#401	Gemini 3.1 Flash Lite Preview high	Google	1.0	0.4	$2.310	2/2	64.0s
Total Tests 2 Wrong Tests 0 Total Cost $2.310 Response Time (avg) 64.0s
#209	Claude Opus 4.8 none	Anthropic	1.0	0.7	$2.334	2/2	1.37s
Total Tests 2 Wrong Tests 0 Total Cost $2.334 Response Time (avg) 1.37s
#56	Claude Opus 5 low	Anthropic	1.0	0.9	$2.350	2/2	4.13s
Total Tests 2 Wrong Tests 0 Total Cost $2.350 Response Time (avg) 4.13s
#205	Ember-1 high	Fireworks	0.7	0.7	$2.405	1/2	33.4s
Total Tests 2 Wrong Tests 1 Total Cost $2.405 Response Time (avg) 33.4s

Instructions following Ranking

Filter models

Top Models by Instructions following Score

Instructions following Score vs Total Cost

Top Models by Response Time (avg)