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

Gemini 3.6 Flash 1.0

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)
#213	Mercury 2.5 Preview medium	Inception	1.0	0.7	$0.039	2/2	1.35s
Total Tests 2 Wrong Tests 0 Total Cost $0.039 Response Time (avg) 1.35s
#214	GPT-6 Sol none	OpenAI	1.0	0.7	$0.551	2/2	1.23s
Total Tests 2 Wrong Tests 0 Total Cost $0.551 Response Time (avg) 1.23s
#217	Grok 4.7 xhigh	X AI	1.0	0.7	$3.398	2/2	17.3s
Total Tests 2 Wrong Tests 0 Total Cost $3.398 Response Time (avg) 17.3s
#218	Grok Build 0.1 medium	X AI	1.0	0.7	$1.419	2/2	12.4s
Total Tests 2 Wrong Tests 0 Total Cost $1.419 Response Time (avg) 12.4s
#222	MiniMax M3 medium	Minimax	1.0	0.7	$0.422	2/2	6.14s
Total Tests 2 Wrong Tests 0 Total Cost $0.422 Response Time (avg) 6.14s
#224	GPT 5.3 Chat default	OpenAI	1.0	0.7	$0.533	2/2	3.51s
Total Tests 2 Wrong Tests 0 Total Cost $0.533 Response Time (avg) 3.51s
#227	GLM 5.3 Flash low	Z.ai	1.0	0.7	$0.038	2/2	1.65s
Total Tests 2 Wrong Tests 0 Total Cost $0.038 Response Time (avg) 1.65s
#229	GLM 5.2 none	Z.ai	1.0	0.7	$0.250	2/2	3.84s
Total Tests 2 Wrong Tests 0 Total Cost $0.250 Response Time (avg) 3.84s
#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
#233	Step 3.7 Flash high	Stepfun	1.0	0.7	$1.478	2/2	1.52s
Total Tests 2 Wrong Tests 0 Total Cost $1.478 Response Time (avg) 1.52s
#234	Beam 1.0 501B A23B medium	Reflection	1.0	0.7	$0.499	2/2	1.24s
Total Tests 2 Wrong Tests 0 Total Cost $0.499 Response Time (avg) 1.24s
#235	KAT-Coder-Pro V2.5 low	Kwaipilot	1.0	0.7	$0.568	2/2	2.53s
Total Tests 2 Wrong Tests 0 Total Cost $0.568 Response Time (avg) 2.53s
#238	Qwen3.6 35B A3B medium	Qwen	1.0	0.7	$0.834	2/2	7.50s
Total Tests 2 Wrong Tests 0 Total Cost $0.834 Response Time (avg) 7.50s
#239	Mercury 2.5 Preview high	Inception	1.0	0.6	$0.040	2/2	1.05s
Total Tests 2 Wrong Tests 0 Total Cost $0.040 Response Time (avg) 1.05s
#241	Beam 1.0 501B A23B xhigh	Reflection	1.0	0.6	$0.688	2/2	1.15s
Total Tests 2 Wrong Tests 0 Total Cost $0.688 Response Time (avg) 1.15s

Instructions following Ranking

Filter models

Top Models by Instructions following Score

Instructions following Score vs Total Cost

Top Models by Response Time (avg)