Puzzle Solving Model Ranking

See which AI models perform best on Puzzle Solving, which ones stay reliable, and where the biggest gaps appear. Sort by: Metric ↑.

Models Shown

Average Puzzle Solving Score

0.7

Best Model

Step 3.5 Flash 0.0

Failure Reasons

With failure reason Wrong answer352 With failure reason Did not follow instructions166 With failure reason API error35 With failure reason Extra formatting16 With failure reason No answer14 With failure reason Timed out11

451/451

Rank	Model	Company	Puzzle Solving Score	Score	Total Cost	Tests Correct	Response Time (avg)
#135	GPT-6 Luna high	OpenAI	0.8	0.8	$0.074	2/3	7.51s
Total Tests 3 Wrong Tests 1 Total Cost $0.074 Response Time (avg) 7.51s
#151	GPT-5.6 Luna medium	OpenAI	0.8	0.7	$0.065	2/3	4.04s
Total Tests 3 Wrong Tests 1 Total Cost $0.065 Response Time (avg) 4.04s
#279	Step 5 Preview medium	Stepfun	0.8	0.6	$4.136	2/3	59.9s
Total Tests 3 Wrong Tests 1 Total Cost $4.136 Response Time (avg) 59.9s
#88	Muse Spark 1.1 high	Meta	0.8	0.8	$2.570	2/3	70.0s
Total Tests 3 Wrong Tests 1 Total Cost $2.570 Response Time (avg) 70.0s
#206	Space Bunny Alpha max	Stealth	0.8	0.7	$0.000	2/3	9.15s
Total Tests 3 Wrong Tests 1 Total Cost $0.000 Response Time (avg) 9.15s
#240	Beam 1.0 501B A23B max	Reflection	0.8	0.6	$0.799	2/3	3.94s
Total Tests 3 Wrong Tests 1 Total Cost $0.799 Response Time (avg) 3.94s
#218	GLM 5.3 Flash low	Z.ai	0.8	0.7	$0.038	2/3	2.67s
Total Tests 3 Wrong Tests 1 Total Cost $0.038 Response Time (avg) 2.67s
#256	Minimax M3.1 Flash medium	Minimax	0.8	0.6	$0.000	2/3	4.18s
Total Tests 3 Wrong Tests 1 Total Cost $0.000 Response Time (avg) 4.18s
#85	Muse Glimmer 30B xhigh	Meta	0.8	0.8	$0.585	2/3	199.7s
Total Tests 3 Wrong Tests 1 Total Cost $0.585 Response Time (avg) 199.7s
#150	Seed-2.0-Code high	Bytedance Seed	0.8	0.7	$1.448	2/3	15.9s
Total Tests 3 Wrong Tests 1 Total Cost $1.448 Response Time (avg) 15.9s
#243	Minimax M3.1 Flash xhigh	Minimax	0.8	0.6	$0.000	2/3	10.2s
Total Tests 3 Wrong Tests 1 Total Cost $0.000 Response Time (avg) 10.2s
#285	MiMo-V2.6-Pro none	Xiaomi	0.8	0.6	$0.193	2/3	1.67s
Total Tests 3 Wrong Tests 1 Total Cost $0.193 Response Time (avg) 1.67s
#213	MiniMax M3 medium	Minimax	0.8	0.7	$0.422	2/3	49.9s
Total Tests 3 Wrong Tests 1 Total Cost $0.422 Response Time (avg) 49.9s
#262	Space Bunny Alpha medium	Stealth	0.8	0.6	$0.000	2/3	3.42s
Total Tests 3 Wrong Tests 1 Total Cost $0.000 Response Time (avg) 3.42s
#30	Muse Spark Open high	Meta	0.8	0.9	$1.782	2/3	145.7s
Total Tests 3 Wrong Tests 1 Total Cost $1.782 Response Time (avg) 145.7s

Puzzle Solving Ranking

Filter models

Top Models by Puzzle Solving Score

Puzzle Solving Score vs Total Cost

Top Models by Response Time (avg)