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: Response Time (avg) ↑.

Models Shown

Average Puzzle Solving Score

0.7

Best Model

Step 3.5 Flash 0.0

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)
#282	Gemini 3.1 Flash Lite none	Google	0.6	0.6	$0.069	1/3	720ms
Total Tests 3 Wrong Tests 2 Total Cost $0.069 Response Time (avg) 720ms
#318	MiMo-V2.6-Flash none	Xiaomi	0.4	0.5	$0.060	0/3	739ms
Total Tests 3 Wrong Tests 3 Total Cost $0.060 Response Time (avg) 739ms
#311	Gemma 4 26B A4B none	Google	0.6	0.5	$0.031	1/3	744ms
Total Tests 3 Wrong Tests 2 Total Cost $0.031 Response Time (avg) 744ms
#397	Nemotron 3.5 Lightning none	NVIDIA	0.3	0.4	$0.009	0/3	750ms
Total Tests 3 Wrong Tests 3 Total Cost $0.009 Response Time (avg) 750ms
#305	Nemotron 3.5 Super VL none	NVIDIA	0.5	0.6	$0.040	0/3	754ms
Total Tests 3 Wrong Tests 3 Total Cost $0.040 Response Time (avg) 754ms
#322	GPT-5.6 Luna none	OpenAI	0.5	0.5	$0.042	1/3	790ms
Total Tests 3 Wrong Tests 2 Total Cost $0.042 Response Time (avg) 790ms
#336	Mercury 2.5 low	Inception	0.6	0.5	$0.020	1/3	792ms
Total Tests 3 Wrong Tests 2 Total Cost $0.020 Response Time (avg) 792ms
#404	Elephant Alpha default	Openrouter	0.4	0.4	$0.000	0/3	807ms
Total Tests 3 Wrong Tests 3 Total Cost $0.000 Response Time (avg) 807ms
#361	Laguna S 2.1 none	Poolside	0.3	0.5	$0.044	0/3	828ms
Total Tests 3 Wrong Tests 3 Total Cost $0.044 Response Time (avg) 828ms
#294	GPT-5.4 Mini none	OpenAI	0.5	0.6	$0.170	1/3	836ms
Total Tests 3 Wrong Tests 2 Total Cost $0.170 Response Time (avg) 836ms
#426	Drex v1.5 default	Nace AI	1.0	0.2	$0.002	0/1	850ms
Total Tests 1 Wrong Tests 1 Total Cost $0.002 Response Time (avg) 850ms
#405	Elephant Alpha medium	Openrouter	0.5	0.4	$0.000	1/3	868ms
Total Tests 3 Wrong Tests 2 Total Cost $0.000 Response Time (avg) 868ms
#403	Laguna M.1 default	Poolside	0.3	0.4	$0.009	0/3	891ms
Total Tests 3 Wrong Tests 3 Total Cost $0.009 Response Time (avg) 891ms
#263	Gemini 3.1 Flash Lite Preview none	Google	1.0	0.6	$0.090	3/3	900ms
Total Tests 3 Wrong Tests 0 Total Cost $0.090 Response Time (avg) 900ms
#269	Inkling none	Thinkingmachines	0.6	0.6	$0.292	1/3	931ms
Total Tests 3 Wrong Tests 2 Total Cost $0.292 Response Time (avg) 931ms

Puzzle Solving Ranking

Filter models

Top Models by Puzzle Solving Score

Puzzle Solving Score vs Total Cost

Top Models by Response Time (avg)