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: Tests Correct ↑.

Models Shown

Average Instructions following Score

0.8

Best Model

Minimax M3.1 Flash 0.5

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)
#37	Muse Wonder medium	Meta	0.7	0.9	$3.397	1/2	3.88s
Total Tests 2 Wrong Tests 1 Total Cost $3.397 Response Time (avg) 3.88s
#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
#45	Muse Spark 1.3 high	Meta	0.7	0.9	$1.891	1/2	14.7s
Total Tests 2 Wrong Tests 1 Total Cost $1.891 Response Time (avg) 14.7s
#46	Muse Wonder low	Meta	0.7	0.9	$2.637	1/2	2.08s
Total Tests 2 Wrong Tests 1 Total Cost $2.637 Response Time (avg) 2.08s
#49	Muse Wonder minimal	Meta	0.7	0.9	$1.639	1/2	1.39s
Total Tests 2 Wrong Tests 1 Total Cost $1.639 Response Time (avg) 1.39s
#59	Muse Spark Open low	Meta	0.8	0.9	$0.600	1/2	10.3s
Total Tests 2 Wrong Tests 1 Total Cost $0.600 Response Time (avg) 10.3s
#62	Muse Spark 1.1 medium	Meta	0.7	0.9	$1.665	1/2	6.31s
Total Tests 2 Wrong Tests 1 Total Cost $1.665 Response Time (avg) 6.31s
#68	Muse Spark Open medium	Meta	0.7	0.9	$1.260	1/2	18.4s
Total Tests 2 Wrong Tests 1 Total Cost $1.260 Response Time (avg) 18.4s
#75	MiMo-V2.6-Pro medium	Xiaomi	0.8	0.9	$0.586	1/2	1.79s
Total Tests 2 Wrong Tests 1 Total Cost $0.586 Response Time (avg) 1.79s
#80	Muse Spark 1.1 low	Meta	0.7	0.9	$0.885	1/2	5.42s
Total Tests 2 Wrong Tests 1 Total Cost $0.885 Response Time (avg) 5.42s
#90	Nemotron 3.5 Super VL high	NVIDIA	0.8	0.8	$0.349	1/2	6.10s
Total Tests 2 Wrong Tests 1 Total Cost $0.349 Response Time (avg) 6.10s
#93	Muse Glimmer 30B xhigh	Meta	0.8	0.8	$0.585	1/2	8.90s
Total Tests 2 Wrong Tests 1 Total Cost $0.585 Response Time (avg) 8.90s
#96	Muse Spark 1.1 high	Meta	0.6	0.8	$2.570	1/2	7.81s
Total Tests 2 Wrong Tests 1 Total Cost $2.570 Response Time (avg) 7.81s
#115	DeepSeek V4 Pro 0423 high	DeepSeek	0.8	0.8	$0.149	1/2	8.73s
Total Tests 2 Wrong Tests 1 Total Cost $0.149 Response Time (avg) 8.73s
#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

Instructions following Ranking

Filter models

Top Models by Instructions following Score

Instructions following Score vs Total Cost

Top Models by Response Time (avg)