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: Metric ↑.

Models Shown

Average Instructions following Score

0.8

Best Model

Gemini 3 Flash Preview 0.0

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)
#228	GPT-5.5 none	OpenAI	0.6	0.7	$1.212	1/2	1.15s
Total Tests 2 Wrong Tests 1 Total Cost $1.212 Response Time (avg) 1.15s
#287	Qwen3.5 Plus 2026-04-20 none	Qwen	0.6	0.6	$0.216	1/2	1.17s
Total Tests 2 Wrong Tests 1 Total Cost $0.216 Response Time (avg) 1.17s
#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
#331	Seed-2.0-Code none	Bytedance Seed	0.6	0.5	$0.257	1/2	1.80s
Total Tests 2 Wrong Tests 1 Total Cost $0.257 Response Time (avg) 1.80s
#345	Qwen3.6 35B A3B none	Qwen	0.6	0.5	$0.105	1/2	1.86s
Total Tests 2 Wrong Tests 1 Total Cost $0.105 Response Time (avg) 1.86s
#403	GLM 4.7 Flash medium	Z.ai	0.6	0.4	$0.193	1/2	2.97s
Total Tests 2 Wrong Tests 1 Total Cost $0.193 Response Time (avg) 2.97s
#155	Space Bunny Alpha high	Stealth	0.6	0.8	$0.000	1/2	2.04s
Total Tests 2 Wrong Tests 1 Total Cost $0.000 Response Time (avg) 2.04s
#262	Qwen3.6 27B none	Qwen	0.6	0.6	$0.148	1/2	1.92s
Total Tests 2 Wrong Tests 1 Total Cost $0.148 Response Time (avg) 1.92s
#140	Qwen3.7 Plus none	Qwen	0.6	0.8	$0.178	1/2	929ms
Total Tests 2 Wrong Tests 1 Total Cost $0.178 Response Time (avg) 929ms
#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
#190	Minimax M3.1 Flash low	Minimax	0.6	0.7	$0.000	1/2	1.60s
Total Tests 2 Wrong Tests 1 Total Cost $0.000 Response Time (avg) 1.60s
#208	Claude Sonnet 5.5 low	Anthropic	0.6	0.7	$0.909	1/2	1.91s
Total Tests 2 Wrong Tests 1 Total Cost $0.909 Response Time (avg) 1.91s
#219	Qwen3.5-Flash none	Qwen	0.6	0.7	$0.089	1/2	8.81s
Total Tests 2 Wrong Tests 1 Total Cost $0.089 Response Time (avg) 8.81s
#236	Claude Sonnet 5.5 medium	Anthropic	0.6	0.7	$1.100	1/2	1.88s
Total Tests 2 Wrong Tests 1 Total Cost $1.100 Response Time (avg) 1.88s
#247	Qwen3.5-122B-A10B none	Qwen	0.6	0.6	$0.308	1/2	513ms
Total Tests 2 Wrong Tests 1 Total Cost $0.308 Response Time (avg) 513ms

Instructions following Ranking

Filter models

Top Models by Instructions following Score

Instructions following Score vs Total Cost

Top Models by Response Time (avg)