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: Response Time (avg) ↓.

Models Shown

Average Instructions following Score

0.8

Best Model

Command A+ 0.3

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)
#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
#364	Grok 4.20 Beta medium	X AI	1.0	0.5	$0.750	2/2	4.89s
Total Tests 2 Wrong Tests 0 Total Cost $0.750 Response Time (avg) 4.89s
#122	Gemini 3.8 Flash medium	Google	1.0	0.8	$0.769	2/2	4.81s
Total Tests 2 Wrong Tests 0 Total Cost $0.769 Response Time (avg) 4.81s
#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
#337	Step 3.5 Flash medium	Stepfun	0.8	0.5	$0.105	1/2	4.78s
Total Tests 2 Wrong Tests 1 Total Cost $0.105 Response Time (avg) 4.78s
#2	Gemini 3.8 Flash high	Google	1.0	1.0	$1.927	2/2	4.73s
Total Tests 2 Wrong Tests 0 Total Cost $1.927 Response Time (avg) 4.73s
#411	Grok 4.1 Fast medium	X AI	0.7	0.4	$0.069	1/2	4.63s
Total Tests 2 Wrong Tests 1 Total Cost $0.069 Response Time (avg) 4.63s
#81	Claude Sonnet 5.5 xhigh	Anthropic	1.0	0.9	$1.516	2/2	4.58s
Total Tests 2 Wrong Tests 0 Total Cost $1.516 Response Time (avg) 4.58s
#97	DeepSeek V4 Flash 0731 high	DeepSeek	1.0	0.8	$0.576	2/2	4.46s
Total Tests 2 Wrong Tests 0 Total Cost $0.576 Response Time (avg) 4.46s
#61	Muse Spark 1.2 medium	Meta	1.0	0.9	$1.590	2/2	4.40s
Total Tests 2 Wrong Tests 0 Total Cost $1.590 Response Time (avg) 4.40s
#146	Nemotron 3.5 Super VL medium	NVIDIA	1.0	0.8	$0.437	2/2	4.34s
Total Tests 2 Wrong Tests 0 Total Cost $0.437 Response Time (avg) 4.34s
#84	Qwen3.8 Max (0902) low	Qwen	1.0	0.9	$1.131	2/2	4.32s
Total Tests 2 Wrong Tests 0 Total Cost $1.131 Response Time (avg) 4.32s
#134	Ling 3.1 Flash high	Inclusionai	1.0	0.8	$0.000	2/2	4.31s
Total Tests 2 Wrong Tests 0 Total Cost $0.000 Response Time (avg) 4.31s
#412	Laguna M.1 medium	Poolside	1.0	0.4	$0.033	2/2	4.30s
Total Tests 2 Wrong Tests 0 Total Cost $0.033 Response Time (avg) 4.30s
#351	MiMo-V2-Flash medium	Xiaomi	1.0	0.5	$0.043	2/2	4.28s
Total Tests 2 Wrong Tests 0 Total Cost $0.043 Response Time (avg) 4.28s

Instructions following Ranking

Filter models

Top Models by Instructions following Score

Instructions following Score vs Total Cost

Top Models by Response Time (avg)