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

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)
#7	GPT-6 Astra high	OpenAI	1.0	1.0	$4.458	2/2	3.58s
Total Tests 2 Wrong Tests 0 Total Cost $4.458 Response Time (avg) 3.58s
#198	Step 5 Preview high	Stepfun	0.7	0.7	$4.513	1/2	20.5s
Total Tests 2 Wrong Tests 1 Total Cost $4.513 Response Time (avg) 20.5s
#30	Claude Opus 5 high	Anthropic	1.0	0.9	$4.524	2/2	4.78s
Total Tests 2 Wrong Tests 0 Total Cost $4.524 Response Time (avg) 4.78s
#98	GLM 5.2 high	Z.ai	1.0	0.8	$4.632	2/2	4.26s
Total Tests 2 Wrong Tests 0 Total Cost $4.632 Response Time (avg) 4.26s
#133	Muse Wonder max	Meta	0.8	0.8	$4.766	1/2	13.2s
Total Tests 2 Wrong Tests 1 Total Cost $4.766 Response Time (avg) 13.2s
#38	GPT-5.5 medium	OpenAI	1.0	0.9	$4.809	2/2	3.36s
Total Tests 2 Wrong Tests 0 Total Cost $4.809 Response Time (avg) 3.36s
#5	GPT-6 Astra max	OpenAI	1.0	1.0	$5.044	2/2	6.34s
Total Tests 2 Wrong Tests 0 Total Cost $5.044 Response Time (avg) 6.34s
#63	Claude Fable 5 medium	Anthropic	1.0	0.9	$5.089	2/2	5.90s
Total Tests 2 Wrong Tests 0 Total Cost $5.089 Response Time (avg) 5.90s
#409	Grok 4.20 Multi Agent Beta medium	X AI	1.0	0.4	$5.599	2/2	3.52s
Total Tests 2 Wrong Tests 0 Total Cost $5.599 Response Time (avg) 3.52s
#8	GPT-6 Astra xhigh	OpenAI	1.0	1.0	$6.213	2/2	4.91s
Total Tests 2 Wrong Tests 0 Total Cost $6.213 Response Time (avg) 4.91s
#39	Claude Sonnet 5.5 max	Anthropic	0.9	0.9	$8.557	1/2	6.24s
Total Tests 2 Wrong Tests 1 Total Cost $8.557 Response Time (avg) 6.24s

Instructions following Ranking