Anti-AI Tricks x Wrong answer Ranking

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

Models Shown

Total Failures

293

Most Affected Model

Failure Reasons

Wrong answer293 Did not follow instructions33 Extra formatting20 API error14 No answer4 Timed out4

Categories

Domain specific412 Anti-AI Tricks293 Coding252 Puzzle Solving201 Trivia168 Combined68 Instructions following61 General Intelligence59 Data parsing and extraction41 Tool Calling3

140/140

Rank	Model	Company	Wrong answer Count	Category Score	Total Cost	Tests Correct	Response Time (avg)
#172	MiniMax M2.7 medium	Minimax	1	7.9	$0.163	2/4	40.3s
Total Tests 4 Wrong Tests 2 Total Cost $0.163 Response Time (avg) 40.3s
#102	Laguna XS 2.1 medium	Poolside	2	4.8	$0.068	1/4	42.0s
Total Tests 4 Wrong Tests 3 Total Cost $0.068 Response Time (avg) 42.0s
#57	Qwen3.5 Plus 2026-02-15 medium	Qwen	1	8.2	$0.437	3/4	45.8s
Total Tests 4 Wrong Tests 1 Total Cost $0.437 Response Time (avg) 45.8s
#77	Kimi K2.5 medium	Moonshot AI	1	7.3	$0.600	2/4	51.4s
Total Tests 4 Wrong Tests 2 Total Cost $0.600 Response Time (avg) 51.4s
#80	Seed-2.0-Mini medium	Bytedance Seed	1	6.6	$0.101	2/4	74.7s
Total Tests 4 Wrong Tests 2 Total Cost $0.101 Response Time (avg) 74.7s

Filter models