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

Claude Opus 5.5 1

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)
#278	Qwen3.5 Plus 2026-04-20 none	Qwen	2	0.6	$0.216	8/23	18.5s
Total Tests 23 Wrong Tests 15 Total Cost $0.216 Response Time (avg) 18.5s
#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
#282	Apodex 1.1 Mini medium	Apodex	2	0.6	$0.000	11/23	32.7s
Total Tests 23 Wrong Tests 12 Total Cost $0.000 Response Time (avg) 32.7s
#298	DeepSeek V4.1 Flash none	DeepSeek	2	0.6	$0.391	7/23	16.6s
Total Tests 23 Wrong Tests 16 Total Cost $0.391 Response Time (avg) 16.6s
#300	Ring 2.6 1t medium	Inclusionai	2	0.6	$0.102	11/23	65.5s
Total Tests 23 Wrong Tests 12 Total Cost $0.102 Response Time (avg) 65.5s
#302	GPT-5 Nano medium	OpenAI	2	0.6	$0.159	8/23	56.5s
Total Tests 23 Wrong Tests 15 Total Cost $0.159 Response Time (avg) 56.5s
#306	Dots 3 Note Preview medium	Dots Studio	2	0.6	$0.000	8/23	70.3s
Total Tests 23 Wrong Tests 15 Total Cost $0.000 Response Time (avg) 70.3s
#308	Space Bunny Alpha low	Stealth	2	0.6	$0.000	8/23	30.6s
Total Tests 23 Wrong Tests 15 Total Cost $0.000 Response Time (avg) 30.6s
#313	Qwen3.5-35B-A3B none	Qwen	2	0.6	$0.120	6/23	18.3s
Total Tests 23 Wrong Tests 17 Total Cost $0.120 Response Time (avg) 18.3s
#314	Nemotron 3.5 Super VL none	NVIDIA	2	0.6	$0.040	8/23	47.0s
Total Tests 23 Wrong Tests 15 Total Cost $0.040 Response Time (avg) 47.0s
#320	Gemma 4 26B A4B none	Google	2	0.5	$0.031	9/23	10.5s
Total Tests 23 Wrong Tests 14 Total Cost $0.031 Response Time (avg) 10.5s
#322	Seed-2.0-Code none	Bytedance Seed	2	0.5	$0.257	6/23	17.5s
Total Tests 23 Wrong Tests 17 Total Cost $0.257 Response Time (avg) 17.5s
#336	Qwen3.6 35B A3B none	Qwen	2	0.5	$0.105	4/23	8.43s
Total Tests 23 Wrong Tests 19 Total Cost $0.105 Response Time (avg) 8.43s
#337	Inkling Small low	Thinkingmachines	2	0.5	$0.055	9/23	1.99s
Total Tests 23 Wrong Tests 14 Total Cost $0.055 Response Time (avg) 1.99s
#343	Mistral Small 4 medium	Mistral	2	0.5	$0.126	5/23	12.7s
Total Tests 23 Wrong Tests 18 Total Cost $0.126 Response Time (avg) 12.7s

Did not follow instructions Failures

Filter models

Top Models by Did not follow instructions Count

Did not follow instructions Count vs Score

Top Models by Response Time (avg)