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: Score ↑.

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)
#18	GPT-5.4 medium	OpenAI	2	8.5	$1.533	15/22	23.1s
Total Tests 22 Wrong Tests 7 Total Cost $1.533 Response Time (avg) 23.1s
#16	Muse Spark 1.1 medium	Meta	2	8.6	$1.357	15/22	25.0s
Total Tests 22 Wrong Tests 7 Total Cost $1.357 Response Time (avg) 25.0s
#13	GPT-5.3-Codex medium	OpenAI	2	8.9	$0.920	16/22	17.0s
Total Tests 22 Wrong Tests 6 Total Cost $0.920 Response Time (avg) 17.0s
#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
#9	Gemini 3.5 Flash medium	Google	1	9.1	$0.642	19/22	8.20s
Total Tests 22 Wrong Tests 3 Total Cost $0.642 Response Time (avg) 8.20s

Did not follow instructions Failures