Puzzle Solving x Wrong answer Ranking

See which AI models are most likely to hit Wrong answer on Puzzle Solving, so you can spot weak points faster. Sort by: Response Time (avg) ↑.

Models Shown

Total Failures

352

Most Affected Model

Failure Reasons

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

Categories

Domain specific893 Anti-AI Tricks519 Coding484 Puzzle Solving352 Trivia315 General Intelligence134 Agentic128 Combined128 Instructions following117 Data parsing and extraction93

246/246

Rank	Model	Company	Wrong answer Count	Category Score	Total Cost	Tests Correct	Response Time (avg)
#332	Granite 4.2 8B low	IBM Granite	2	0.3	$0.036	0/3	90.8s
Total Tests 3 Wrong Tests 3 Total Cost $0.036 Response Time (avg) 90.8s
#68	MiMo-V2.6-Pro medium	Xiaomi	1	0.8	$0.586	2/3	92.2s
Total Tests 3 Wrong Tests 1 Total Cost $0.586 Response Time (avg) 92.2s
#389	Granite 4.2 8B none	IBM Granite	1	0.3	$0.037	0/3	107.6s
Total Tests 3 Wrong Tests 3 Total Cost $0.037 Response Time (avg) 107.6s
#189	Step 5 Preview high	Stepfun	1	0.6	$4.513	1/3	143.2s
Total Tests 3 Wrong Tests 2 Total Cost $4.513 Response Time (avg) 143.2s
#326	Hy4 preview low	Tencent	2	0.5	$1.844	0/3	238.0s
Total Tests 3 Wrong Tests 3 Total Cost $1.844 Response Time (avg) 238.0s
#407	Xing4.0 29b A4b medium	Xingchen AGI	1	0.3	$0.000	0/3	257.1s
Total Tests 3 Wrong Tests 3 Total Cost $0.000 Response Time (avg) 257.1s

Filter models