Anti-AI Tricks Model Ranking

See which AI models perform best on Anti-AI Tricks, which ones stay reliable, and where the biggest gaps appear. Sort by: Tests Correct ↓.

Models Shown

Average Anti-AI Tricks Score

0.7

Best Model

Gemini 3.6 Flash 1.0

Failure Reasons

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

442/442

Rank	Model	Company	Anti-AI Tricks Score	Score	Total Cost	Tests Correct	Response Time (avg)
#102	Seed-2.0-Lite medium	Bytedance Seed	0.8	0.8	$0.271	3/4	18.0s
Total Tests 4 Wrong Tests 1 Total Cost $0.271 Response Time (avg) 18.0s
#103	Seed-2.0-Code low	Bytedance Seed	0.9	0.8	$0.881	3/4	39.6s
Total Tests 4 Wrong Tests 1 Total Cost $0.881 Response Time (avg) 39.6s
#105	Claude Opus 4.7 medium	Anthropic	0.8	0.8	$3.636	3/4	1.85s
Total Tests 4 Wrong Tests 1 Total Cost $3.636 Response Time (avg) 1.85s
#106	DeepSeek V4 Flash 0423 high	DeepSeek	0.8	0.8	$0.261	3/4	28.5s
Total Tests 4 Wrong Tests 1 Total Cost $0.261 Response Time (avg) 28.5s
#107	DeepSeek V4.1 Flash low	DeepSeek	0.8	0.8	$0.494	3/4	3.32s
Total Tests 4 Wrong Tests 1 Total Cost $0.494 Response Time (avg) 3.32s
#108	GPT-5.6 Luna high	OpenAI	0.8	0.8	$0.118	3/4	2.99s
Total Tests 4 Wrong Tests 1 Total Cost $0.118 Response Time (avg) 2.99s
#110	GPT-5.4 Nano medium	OpenAI	0.8	0.8	$0.235	3/4	4.52s
Total Tests 4 Wrong Tests 1 Total Cost $0.235 Response Time (avg) 4.52s
#113	GPT-5.6 Terra low	OpenAI	0.8	0.8	$0.435	3/4	2.36s
Total Tests 4 Wrong Tests 1 Total Cost $0.435 Response Time (avg) 2.36s
#114	Qwen3.5-27B medium	Qwen	0.9	0.8	$1.135	3/4	19.8s
Total Tests 4 Wrong Tests 1 Total Cost $1.135 Response Time (avg) 19.8s
#117	GPT-5.4 Mini medium	OpenAI	0.9	0.8	$1.102	3/4	4.05s
Total Tests 4 Wrong Tests 1 Total Cost $1.102 Response Time (avg) 4.05s
#126	Step 3.7 Flash medium	Stepfun	0.9	0.8	$0.571	3/4	9.65s
Total Tests 4 Wrong Tests 1 Total Cost $0.571 Response Time (avg) 9.65s
#130	DeepSeek V4 Flash 0731 medium	DeepSeek	0.8	0.8	$0.460	3/4	18.0s
Total Tests 4 Wrong Tests 1 Total Cost $0.460 Response Time (avg) 18.0s
#131	Muse Wonder high	Meta	0.8	0.8	$3.426	3/4	5.93s
Total Tests 4 Wrong Tests 1 Total Cost $3.426 Response Time (avg) 5.93s
#133	Muse Glimmer 30B high	Meta	0.9	0.8	$0.506	3/4	13.2s
Total Tests 4 Wrong Tests 1 Total Cost $0.506 Response Time (avg) 13.2s
#135	Claude Haiku 5.5 medium	Anthropic	0.9	0.8	$0.063	3/4	2.36s
Total Tests 4 Wrong Tests 1 Total Cost $0.063 Response Time (avg) 2.36s

Anti-AI Tricks Ranking

Filter models

Top Models by Anti-AI Tricks Score

Anti-AI Tricks Score vs Total Cost

Top Models by Response Time (avg)