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: Total Cost ↑.

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)
#236	Claude Sonnet 4.6 medium	Anthropic	1	0.7	$2.126	2/4	2.98s
Total Tests 4 Wrong Tests 2 Total Cost $2.126 Response Time (avg) 2.98s
#60	GPT-5.4 medium	OpenAI	1	0.8	$2.213	3/4	4.11s
Total Tests 4 Wrong Tests 1 Total Cost $2.213 Response Time (avg) 4.11s
#87	Muse Spark 1.1 high	Meta	1	0.7	$2.570	2/4	8.60s
Total Tests 4 Wrong Tests 2 Total Cost $2.570 Response Time (avg) 8.60s
#175	Claude Opus 5 none	Anthropic	3	0.6	$2.766	1/4	4.33s
Total Tests 4 Wrong Tests 3 Total Cost $2.766 Response Time (avg) 4.33s
#105	Claude Opus 4.7 medium	Anthropic	1	0.8	$3.636	3/4	1.85s
Total Tests 4 Wrong Tests 1 Total Cost $3.636 Response Time (avg) 1.85s
#302	Step 5 Preview low	Stepfun	1	0.7	$4.110	2/4	9.50s
Total Tests 4 Wrong Tests 2 Total Cost $4.110 Response Time (avg) 9.50s
#271	Step 5 Preview medium	Stepfun	1	0.6	$4.136	2/4	12.6s
Total Tests 4 Wrong Tests 2 Total Cost $4.136 Response Time (avg) 12.6s
#185	Step 5 Preview high	Stepfun	1	0.7	$4.513	2/4	14.7s
Total Tests 4 Wrong Tests 2 Total Cost $4.513 Response Time (avg) 14.7s
#391	Grok 4.20 Multi Agent Beta medium	X AI	1	0.7	$5.599	2/4	3.46s
Total Tests 4 Wrong Tests 2 Total Cost $5.599 Response Time (avg) 3.46s

Filter models