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)
#312	GLM 5 none	Z.ai	0.8	0.6	$0.140	2/3	1.91s
Total Tests 3 Wrong Tests 1 Total Cost $0.140 Response Time (avg) 1.91s
#317	Ling 3.1 Flash none	Inclusionai	0.8	0.5	$0.000	2/3	3.31s
Total Tests 3 Wrong Tests 1 Total Cost $0.000 Response Time (avg) 3.31s
#318	Gemini 2.5 Flash none	Google	0.8	0.5	$0.017	2/3	604ms
Total Tests 3 Wrong Tests 1 Total Cost $0.017 Response Time (avg) 604ms
#321	GLM 5V Turbo medium	Z.ai	0.8	0.5	$0.457	2/3	10.2s
Total Tests 3 Wrong Tests 1 Total Cost $0.457 Response Time (avg) 10.2s
#322	Seed-2.0-Code none	Bytedance Seed	0.8	0.5	$0.257	2/3	10.0s
Total Tests 3 Wrong Tests 1 Total Cost $0.257 Response Time (avg) 10.0s
#330	Hy3 preview medium	Tencent	0.8	0.5	$0.049	2/3	11.1s
Total Tests 3 Wrong Tests 1 Total Cost $0.049 Response Time (avg) 11.1s
#342	MiMo-V2-Flash medium	Xiaomi	0.8	0.5	$0.043	2/3	3.87s
Total Tests 3 Wrong Tests 1 Total Cost $0.043 Response Time (avg) 3.87s
#365	Hy3 preview high	Tencent	0.8	0.5	$0.135	2/3	27.9s
Total Tests 3 Wrong Tests 1 Total Cost $0.135 Response Time (avg) 27.9s
#384	Ring 2.6 1t default	Inclusionai	0.8	0.4	$0.026	2/3	31.5s
Total Tests 3 Wrong Tests 1 Total Cost $0.026 Response Time (avg) 31.5s
#392	Gemini 3.1 Flash Lite Preview high	Google	0.8	0.4	$2.310	2/3	46.7s
Total Tests 3 Wrong Tests 1 Total Cost $2.310 Response Time (avg) 46.7s
#411	Grok 4.20 Beta default	X AI	0.8	0.4	$0.087	2/3	586ms
Total Tests 3 Wrong Tests 1 Total Cost $0.087 Response Time (avg) 586ms
#284	GLM 5.3 FlashX low	Z.ai	0.8	0.6	$0.157	2/3	1.89s
Total Tests 3 Wrong Tests 1 Total Cost $0.157 Response Time (avg) 1.89s
#138	Claude Haiku 5.5 medium	Anthropic	0.8	0.8	$0.063	2/3	2.67s
Total Tests 3 Wrong Tests 1 Total Cost $0.063 Response Time (avg) 2.67s
#119	GPT-5.4 Mini medium	OpenAI	0.8	0.8	$1.102	2/3	4.37s
Total Tests 3 Wrong Tests 1 Total Cost $1.102 Response Time (avg) 4.37s
#123	MiMo-V2.6-Flash medium	Xiaomi	0.8	0.8	$0.218	2/3	52.9s
Total Tests 3 Wrong Tests 1 Total Cost $0.218 Response Time (avg) 52.9s

Puzzle Solving Ranking

Filter models

Top Models by Puzzle Solving Score

Puzzle Solving Score vs Total Cost

Top Models by Response Time (avg)