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: Total Cost ↑.

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)
#272	Claude Fable 5.1 low	Anthropic	3	0.6	$3.395	11/23	11.4s
Total Tests 23 Wrong Tests 12 Total Cost $3.395 Response Time (avg) 11.4s
#311	Step 5 Preview low	Stepfun	1	0.6	$4.110	10/23	138.3s
Total Tests 23 Wrong Tests 13 Total Cost $4.110 Response Time (avg) 138.3s
#279	Step 5 Preview medium	Stepfun	2	0.6	$4.136	10/23	136.1s
Total Tests 23 Wrong Tests 13 Total Cost $4.136 Response Time (avg) 136.1s
#189	Step 5 Preview high	Stepfun	1	0.7	$4.513	10/23	154.4s
Total Tests 23 Wrong Tests 13 Total Cost $4.513 Response Time (avg) 154.4s
#90	GLM 5.2 high	Z.ai	1	0.8	$4.632	15/23	69.1s
Total Tests 23 Wrong Tests 8 Total Cost $4.632 Response Time (avg) 69.1s
#124	Muse Wonder max	Meta	1	0.8	$4.766	16/23	44.4s
Total Tests 23 Wrong Tests 7 Total Cost $4.766 Response Time (avg) 44.4s
#400	Grok 4.20 Multi Agent Beta medium	X AI	2	0.4	$5.599	8/18	9.69s
Total Tests 18 Wrong Tests 10 Total Cost $5.599 Response Time (avg) 9.69s
#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

Did not follow instructions Failures