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: Total Cost ↑.

Models Shown

Average Puzzle Solving Score

0.7

Best Model

Failure Reasons

With failure reason Wrong answer344 With failure reason Did not follow instructions160 With failure reason API error35 With failure reason Extra formatting16 With failure reason No answer14 With failure reason Timed out11

442/442

Rank	Model	Company	Puzzle Solving Score	Score	Total Cost	Tests Correct	Response Time (avg)
#122	Muse Wonder max	Meta	0.8	0.8	$4.766	2/3	8.97s
Total Tests 3 Wrong Tests 1 Total Cost $4.766 Response Time (avg) 8.97s
#33	GPT-5.5 medium	OpenAI	1.0	0.9	$4.809	3/3	6.76s
Total Tests 3 Wrong Tests 0 Total Cost $4.809 Response Time (avg) 6.76s
#5	GPT-6 Astra max	OpenAI	1.0	1.0	$5.044	3/3	7.32s
Total Tests 3 Wrong Tests 0 Total Cost $5.044 Response Time (avg) 7.32s
#57	Claude Fable 5 medium	Anthropic	0.8	0.9	$5.089	2/3	5.18s
Total Tests 3 Wrong Tests 1 Total Cost $5.089 Response Time (avg) 5.18s
#391	Grok 4.20 Multi Agent Beta medium	X AI	0.7	0.4	$5.599	1/3	5.19s
Total Tests 3 Wrong Tests 2 Total Cost $5.599 Response Time (avg) 5.19s
#8	GPT-6 Astra xhigh	OpenAI	1.0	1.0	$6.213	3/3	4.48s
Total Tests 3 Wrong Tests 0 Total Cost $6.213 Response Time (avg) 4.48s
#34	Claude Sonnet 5.5 max	Anthropic	1.0	0.9	$8.557	3/3	6.17s
Total Tests 3 Wrong Tests 0 Total Cost $8.557 Response Time (avg) 6.17s

Puzzle Solving Ranking