Instructions following Model Ranking

See which AI models perform best on Instructions following, which ones stay reliable, and where the biggest gaps appear. Sort by: Tests Correct ↑.

Models Shown

Average Instructions following Score

0.8

Best Model

Minimax M3.1 Flash 0.5

Failure Reasons

With failure reason Wrong answer118 With failure reason Did not follow instructions82 With failure reason API error25 With failure reason Extra formatting8 With failure reason Timed out5 With failure reason No answer2

461/461

Rank	Model	Company	Instructions following Score	Score	Total Cost	Tests Correct	Response Time (avg)
#306	GPT-5.6 Terra none	OpenAI	0.9	0.6	$0.377	1/2	1.15s
Total Tests 2 Wrong Tests 1 Total Cost $0.377 Response Time (avg) 1.15s
#307	DeepSeek V4.1 Flash none	DeepSeek	0.7	0.6	$0.391	1/2	6.81s
Total Tests 2 Wrong Tests 1 Total Cost $0.391 Response Time (avg) 6.81s
#310	Trinity Large Thinking high	Arcee AI	0.6	0.6	$0.794	1/2	4.12s
Total Tests 2 Wrong Tests 1 Total Cost $0.794 Response Time (avg) 4.12s
#312	GPT-5.4 Mini none	OpenAI	0.6	0.6	$0.170	1/2	728ms
Total Tests 2 Wrong Tests 1 Total Cost $0.170 Response Time (avg) 728ms
#313	Mistral Large 4 none	Mistral	0.7	0.6	$0.290	1/2	1.16s
Total Tests 2 Wrong Tests 1 Total Cost $0.290 Response Time (avg) 1.16s
#315	Dots 3 Note Preview medium	Dots Studio	0.8	0.6	$0.000	1/2	7.77s
Total Tests 2 Wrong Tests 1 Total Cost $0.000 Response Time (avg) 7.77s
#316	Gemma 4 31B none	Google	0.7	0.6	$0.031	1/2	2.84s
Total Tests 2 Wrong Tests 1 Total Cost $0.031 Response Time (avg) 2.84s
#318	GPT-5.4 none	OpenAI	0.7	0.6	$0.690	1/2	1.07s
Total Tests 2 Wrong Tests 1 Total Cost $0.690 Response Time (avg) 1.07s
#319	Solar Pro 4 none	Upstage	0.6	0.6	$0.022	1/2	1.67s
Total Tests 2 Wrong Tests 1 Total Cost $0.022 Response Time (avg) 1.67s
#322	Qwen3.5-35B-A3B none	Qwen	0.6	0.6	$0.120	1/2	809ms
Total Tests 2 Wrong Tests 1 Total Cost $0.120 Response Time (avg) 809ms
#324	Nemotron 3 Super medium	NVIDIA	0.7	0.6	$0.081	1/2	6.97s
Total Tests 2 Wrong Tests 1 Total Cost $0.081 Response Time (avg) 6.97s
#325	Kimi K2.6 none	Moonshot AI	0.7	0.5	$0.486	1/2	1.64s
Total Tests 2 Wrong Tests 1 Total Cost $0.486 Response Time (avg) 1.64s
#326	Ling 3.1 Flash none	Inclusionai	0.8	0.5	$0.000	1/2	1.22s
Total Tests 2 Wrong Tests 1 Total Cost $0.000 Response Time (avg) 1.22s
#328	GPT-6 Luna none	OpenAI	0.6	0.5	$0.026	1/2	17.0s
Total Tests 2 Wrong Tests 1 Total Cost $0.026 Response Time (avg) 17.0s
#329	Gemma 4 26B A4B none	Google	0.6	0.5	$0.031	1/2	690ms
Total Tests 2 Wrong Tests 1 Total Cost $0.031 Response Time (avg) 690ms

←

1 9 10 11 31

→

Instructions following Ranking

Filter models

Top Models by Instructions following Score

Instructions following Score vs Total Cost

Top Models by Response Time (avg)