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

245

Most Affected Model

Categories

In category Puzzle Solving90 In category General Intelligence78 In category Anti-AI Tricks33 In category Instructions following18 In category Coding16 In category Tool Calling8 In category Combined1 In category Domain specific1

140/140

Rank	Model	Company	Did not follow instructions Count	Score	Total Cost	Tests Correct	Response Time (avg)
#12	Grok 4.5 high	X AI	1	8.9	$1.707	17/22	76.5s
Total Tests 22 Wrong Tests 5 Total Cost $1.707 Response Time (avg) 76.5s
#143	Gemini 3.1 Flash Lite high	Google	3	5.6	$2.044	10/18	62.0s
Total Tests 18 Wrong Tests 8 Total Cost $2.044 Response Time (avg) 62.0s
#163	Gemini 3.1 Flash Lite Preview high	Google	1	5.3	$2.310	13/16	68.1s
Total Tests 16 Wrong Tests 3 Total Cost $2.310 Response Time (avg) 68.1s
#43	Claude Opus 4.6 medium	Anthropic	1	7.7	$3.059	13/22	34.3s
Total Tests 22 Wrong Tests 9 Total Cost $3.059 Response Time (avg) 34.3s
#181	Grok 4.20 Multi Agent Beta medium	X AI	2	4.8	$5.599	8/18	9.69s
Total Tests 18 Wrong Tests 10 Total Cost $5.599 Response Time (avg) 9.69s

Did not follow instructions Failures