Instructions following x Extra formatting Ranking

See which AI models are most likely to hit Extra formatting on Instructions following, so you can spot weak points faster. Sort by: Tests Correct ↑.

Models Shown

Total Failures

Most Affected Model

Failure Reasons

Wrong answer111 Did not follow instructions73 API error25 Extra formatting8 Timed out5 No answer2

Categories

Coding37 Domain specific36 Anti-AI Tricks34 Puzzle Solving16 Data parsing and extraction12 Instructions following8 Combined1

8/8

Rank	Model	Company	Extra formatting Count	Category Score	Total Cost	Tests Correct	Response Time (avg)
#380	Granite 4.2 8B none	IBM Granite	1	0.3	$0.037	0/2	79.5s
Total Tests 2 Wrong Tests 2 Total Cost $0.037 Response Time (avg) 79.5s
#130	DeepSeek V4 Flash 0731 medium	DeepSeek	1	0.8	$0.460	1/2	2.42s
Total Tests 2 Wrong Tests 1 Total Cost $0.460 Response Time (avg) 2.42s
#222	Claude Sonnet 5.5 medium	Anthropic	1	0.6	$1.100	1/2	1.88s
Total Tests 2 Wrong Tests 1 Total Cost $1.100 Response Time (avg) 1.88s
#257	DeepSeek V4 Flash 0423 none	DeepSeek	1	0.7	$0.149	1/2	17.5s
Total Tests 2 Wrong Tests 1 Total Cost $0.149 Response Time (avg) 17.5s
#264	Claude Fable 5.1 low	Anthropic	1	0.7	$3.395	1/2	5.24s
Total Tests 2 Wrong Tests 1 Total Cost $3.395 Response Time (avg) 5.24s
#284	Claude Sonnet 5 none	Anthropic	1	0.6	$1.095	1/2	2.58s
Total Tests 2 Wrong Tests 1 Total Cost $1.095 Response Time (avg) 2.58s
#313	Seed-2.0-Code none	Bytedance Seed	1	0.6	$0.257	1/2	1.80s
Total Tests 2 Wrong Tests 1 Total Cost $0.257 Response Time (avg) 1.80s
#410	Hy3 preview none	Tencent	1	0.6	$0.007	1/2	13.0s
Total Tests 2 Wrong Tests 1 Total Cost $0.007 Response Time (avg) 13.0s

Filter models