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: Failure Count ↑.

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)
#405	Granite 4.1 8b default	IBM Granite	4	0.4	$0.007	2/23	1.38s
Total Tests 23 Wrong Tests 21 Total Cost $0.007 Response Time (avg) 1.38s
#409	Ling 3.0 Tiny low	Inclusionai	4	0.4	$0.000	4/23	63.2s
Total Tests 23 Wrong Tests 19 Total Cost $0.000 Response Time (avg) 63.2s
#410	Ling 3.0 Tiny medium	Inclusionai	4	0.4	$0.000	4/23	65.0s
Total Tests 23 Wrong Tests 19 Total Cost $0.000 Response Time (avg) 65.0s
#419	Hy3 preview none	Tencent	4	0.3	$0.007	4/21	12.9s
Total Tests 21 Wrong Tests 17 Total Cost $0.007 Response Time (avg) 12.9s
#199	Claude Sonnet 5.5 low	Anthropic	5	0.7	$0.909	10/23	7.46s
Total Tests 23 Wrong Tests 13 Total Cost $0.909 Response Time (avg) 7.46s
#317	Ling 3.1 Flash none	Inclusionai	5	0.5	$0.000	5/23	15.7s
Total Tests 23 Wrong Tests 18 Total Cost $0.000 Response Time (avg) 15.7s
#351	MiniMax M2.7 medium	Minimax	5	0.5	$0.326	5/23	50.3s
Total Tests 23 Wrong Tests 18 Total Cost $0.326 Response Time (avg) 50.3s
#421	Xing4.0 29b A4b none	Xingchen AGI	5	0.3	$0.000	0/23	42.7s
Total Tests 23 Wrong Tests 23 Total Cost $0.000 Response Time (avg) 42.7s

Did not follow instructions Failures