Did not follow instructions Failure Ranking

See which AI models run into Did not follow instructions most often, so you can spot reliability risks before choosing one. Sort by: Tests Correct ↑.

Models Shown

Total Failures

522

Most Affected Model

Categories

In category Puzzle Solving166 In category General Intelligence142 In category Instructions following77 In category Anti-AI Tricks52 In category Coding50 In category Tool Calling13 In category Agentic10 In category Data parsing and extraction8 In category Domain specific3 In category Combined1

293/293

Rank	Model	Company	Did not follow instructions Count	Score	Total Cost	Tests Correct	Response Time (avg)
#355	Grok 4.20 Beta medium	X AI	1	0.5	$0.750	14/18	9.75s
Total Tests 18 Wrong Tests 4 Total Cost $0.750 Response Time (avg) 9.75s
#34	Claude Sonnet 5.5 max	Anthropic	2	0.9	$8.557	18/23	84.3s
Total Tests 23 Wrong Tests 5 Total Cost $8.557 Response Time (avg) 84.3s
#37	Qwen3.8 Max (0902) high	Qwen	1	0.9	$3.306	18/23	186.1s
Total Tests 23 Wrong Tests 5 Total Cost $3.306 Response Time (avg) 186.1s
#39	Claude Haiku 5.5 xhigh	Anthropic	1	0.9	$0.140	18/23	16.6s
Total Tests 23 Wrong Tests 5 Total Cost $0.140 Response Time (avg) 16.6s
#121	Gemini 3.5 Flash medium	Google	1	0.8	$1.316	18/23	11.8s
Total Tests 23 Wrong Tests 5 Total Cost $1.316 Response Time (avg) 11.8s
#392	Gemini 3.1 Flash Lite Preview high	Google	1	0.4	$2.310	13/16	68.1s
Total Tests 16 Wrong Tests 3 Total Cost $2.310 Response Time (avg) 68.1s
#24	Claude Opus 5.5 low	Anthropic	1	0.9	$1.733	19/23	25.7s
Total Tests 23 Wrong Tests 4 Total Cost $1.733 Response Time (avg) 25.7s
#25	Claude Opus 5.5 high	Anthropic	1	0.9	$2.133	19/23	27.6s
Total Tests 23 Wrong Tests 4 Total Cost $2.133 Response Time (avg) 27.6s

Did not follow instructions Failures