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: Total Cost ↓.

Models Shown

Average Instructions following Score

0.8

Best Model

Claude Sonnet 5.5 0.9

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)
#206	Gemma 4 31B medium	Google	1.0	0.7	$0.144	2/2	12.8s
Total Tests 2 Wrong Tests 0 Total Cost $0.144 Response Time (avg) 12.8s
#157	Seed-2.0-Mini medium	Bytedance Seed	1.0	0.8	$0.140	2/2	17.5s
Total Tests 2 Wrong Tests 0 Total Cost $0.140 Response Time (avg) 17.5s
#321	GLM 5 none	Z.ai	1.0	0.6	$0.140	2/2	1.48s
Total Tests 2 Wrong Tests 0 Total Cost $0.140 Response Time (avg) 1.48s
#44	Claude Haiku 5.5 xhigh	Anthropic	1.0	0.9	$0.140	2/2	3.34s
Total Tests 2 Wrong Tests 0 Total Cost $0.140 Response Time (avg) 3.34s
#300	Qwen3.6 Flash none	Qwen	0.6	0.6	$0.139	1/2	1.10s
Total Tests 2 Wrong Tests 1 Total Cost $0.139 Response Time (avg) 1.10s
#374	Hy3 preview high	Tencent	1.0	0.5	$0.135	2/2	34.4s
Total Tests 2 Wrong Tests 0 Total Cost $0.135 Response Time (avg) 34.4s
#356	MiMo-V2.5-Pro none	Xiaomi	0.6	0.5	$0.135	1/2	1.03s
Total Tests 2 Wrong Tests 1 Total Cost $0.135 Response Time (avg) 1.03s
#192	MiMo-V2.5 medium	Xiaomi	1.0	0.7	$0.130	2/2	1.80s
Total Tests 2 Wrong Tests 0 Total Cost $0.130 Response Time (avg) 1.80s
#352	Mistral Small 4 medium	Mistral	0.7	0.5	$0.126	1/2	1.38s
Total Tests 2 Wrong Tests 1 Total Cost $0.126 Response Time (avg) 1.38s
#232	Mercury 2 medium	Inception	1.0	0.7	$0.121	2/2	1.07s
Total Tests 2 Wrong Tests 0 Total Cost $0.121 Response Time (avg) 1.07s
#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
#382	DeepSeek V3.2 none	DeepSeek	1.0	0.5	$0.119	2/2	1.52s
Total Tests 2 Wrong Tests 0 Total Cost $0.119 Response Time (avg) 1.52s
#119	GPT-5.6 Luna high	OpenAI	1.0	0.8	$0.118	2/2	1.79s
Total Tests 2 Wrong Tests 0 Total Cost $0.118 Response Time (avg) 1.79s
#177	Qwen3.5-27B none	Qwen	0.6	0.7	$0.116	1/2	1.03s
Total Tests 2 Wrong Tests 1 Total Cost $0.116 Response Time (avg) 1.03s
#296	Seed-2.0-Lite none	Bytedance Seed	1.0	0.6	$0.114	2/2	1.06s
Total Tests 2 Wrong Tests 0 Total Cost $0.114 Response Time (avg) 1.06s

Instructions following Ranking

Filter models

Top Models by Instructions following Score

Instructions following Score vs Total Cost

Top Models by Response Time (avg)