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

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)
#169	Gemini 3.1 Flash Lite Preview high	Google	9.8	5.3	$2.310	2/2	64.0s
Total Tests 2 Wrong Tests 0 Total Cost $2.310 Response Time (avg) 64.0s
#47	Claude Opus 4.6 medium	Anthropic	10.0	7.7	$3.059	2/2	2.43s
Total Tests 2 Wrong Tests 0 Total Cost $3.059 Response Time (avg) 2.43s
#37	Kimi K3 max	Moonshot AI	10.0	8.0	$3.112	2/2	7.66s
Total Tests 2 Wrong Tests 0 Total Cost $3.112 Response Time (avg) 7.66s
#20	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
#13	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
#187	Grok 4.20 Multi Agent Beta medium	X AI	9.8	4.8	$5.599	2/2	3.52s
Total Tests 2 Wrong Tests 0 Total Cost $5.599 Response Time (avg) 3.52s

Instructions following Ranking