Puzzle Solving Model Ranking

AI BENCHY Category

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

Models Shown

Average Puzzle Solving Score

6.7

Best Model

Failure Reasons

With failure reason Wrong answer147 With failure reason Did not follow instructions78 With failure reason API error13 With failure reason Extra formatting5 With failure reason Timed out5 With failure reason No answer1

Rank	Model	Company	Puzzle Solving Score	Score	Tests Correct	Response Time (avg)
#72	DeepSeek V3.2 medium	DeepSeek	7.0	7.0	1/3	37.7s
#123	MiMo-V2.5-Pro none	Xiaomi	6.7	5.5	1/3	1.30s
#43	MiMo-V2.5-Pro medium	Xiaomi	6.7	7.5	1/3	5.31s
#84	Grok 4.20 Multi Agent Beta medium	X AI	6.7	6.6	1/3	5.19s
#114	Qwen3.5 Plus 2026-04-20 none	Qwen	6.7	5.7	1/3	1.97s
#115	Qwen3.5-27B none	Qwen	6.7	5.7	1/3	1.38s
#85	Gemma 4 31B none	Google	6.5	6.5	1/3	4.23s
#51	Mimo V2 PRO medium	Xiaomi	6.4	7.4	1/3	5.08s
#122	GLM 4.7 Flash none	Z.ai	6.4	5.5	1/3	1.20s
#100	Grok Build 0.1 none	X AI	6.4	6.0	1/3	9.55s
#90	Gemini 3.1 Flash Lite none	Google	6.3	6.4	1/3	720ms
#102	Gemma 4 26B A4B none	Google	6.2	6.0	1/3	744ms
#79	Hunter Alpha medium	OpenRouter	6.1	6.7	1/3	5.35s
#60	Kimi K2.6 medium	Moonshot AI	6.0	7.2	1/3	25.1s
#126	gpt-oss-120b none	OpenAI	6.0	5.4	1/3	8.21s

Puzzle Solving Ranking