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

502

Most Affected Model

Failure Reasons

Wrong answer502 Did not follow instructions52 API error44 Extra formatting34 No answer13 Timed out8

Categories

Domain specific878 Anti-AI Tricks502 Coding477 Puzzle Solving344 Trivia306 General Intelligence129 Agentic126 Combined126 Instructions following111 Data parsing and extraction93

249/249

Rank	Model	Company	Wrong answer Count	Category Score	Total Cost	Tests Correct	Response Time (avg)
#42	Seed 2.1 Turbo high	Bytedance Seed	1	0.8	$1.892	3/4	47.0s
Total Tests 4 Wrong Tests 1 Total Cost $1.892 Response Time (avg) 47.0s
#237	Kimi K2.5 medium	Moonshot AI	1	0.7	$0.841	2/4	51.4s
Total Tests 4 Wrong Tests 2 Total Cost $0.841 Response Time (avg) 51.4s
#340	Laguna S 2.1 medium	Poolside	3	0.3	$0.092	0/4	51.8s
Total Tests 4 Wrong Tests 4 Total Cost $0.092 Response Time (avg) 51.8s
#349	Laguna S 2.1 high	Poolside	3	0.3	$0.145	0/4	52.2s
Total Tests 4 Wrong Tests 4 Total Cost $0.145 Response Time (avg) 52.2s
#145	Seed-2.0-Mini medium	Bytedance Seed	1	0.7	$0.140	2/4	74.7s
Total Tests 4 Wrong Tests 2 Total Cost $0.140 Response Time (avg) 74.7s
#368	Laguna S 2.1 low	Poolside	4	0.3	$0.108	0/4	80.7s
Total Tests 4 Wrong Tests 4 Total Cost $0.108 Response Time (avg) 80.7s
#317	Hy4 preview low	Tencent	4	0.6	$1.844	0/4	129.6s
Total Tests 4 Wrong Tests 4 Total Cost $1.844 Response Time (avg) 129.6s
#398	Xing4.0 29b A4b medium	Xingchen AGI	3	0.4	$0.000	0/4	145.4s
Total Tests 4 Wrong Tests 4 Total Cost $0.000 Response Time (avg) 145.4s
#61	Muse Spark Open medium	Meta	1	0.7	$1.260	2/4	175.4s
Total Tests 4 Wrong Tests 2 Total Cost $1.260 Response Time (avg) 175.4s

Filter models