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

DeepSeek V4 Pro 0423 0.3

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)
#325	Qwen3.6 Max Preview none	Qwen	0.5	0.5	$0.228	1/4	2.63s
Total Tests 4 Wrong Tests 3 Total Cost $0.228 Response Time (avg) 2.63s
#326	Laguna XS 2.1 none	Poolside	0.5	0.5	$0.020	1/4	755ms
Total Tests 4 Wrong Tests 3 Total Cost $0.020 Response Time (avg) 755ms
#329	Ling 3.0 Flash none	Inclusionai	0.5	0.5	$0.004	1/4	3.34s
Total Tests 4 Wrong Tests 3 Total Cost $0.004 Response Time (avg) 3.34s
#330	Nemotron 3.5 Lightning high	NVIDIA	0.6	0.5	$0.168	1/4	10.3s
Total Tests 4 Wrong Tests 3 Total Cost $0.168 Response Time (avg) 10.3s
#334	Mistral Small 4 medium	Mistral	0.6	0.5	$0.126	1/4	2.67s
Total Tests 4 Wrong Tests 3 Total Cost $0.126 Response Time (avg) 2.67s
#341	Mercury 2.5 Preview low	Inception	0.6	0.5	$0.015	1/4	759ms
Total Tests 4 Wrong Tests 3 Total Cost $0.015 Response Time (avg) 759ms
#344	GPT-4o-mini default	OpenAI	0.5	0.5	$0.024	1/4	1.34s
Total Tests 4 Wrong Tests 3 Total Cost $0.024 Response Time (avg) 1.34s
#357	GLM 4.7 Flash none	Z.ai	0.5	0.5	$0.027	1/4	5.51s
Total Tests 4 Wrong Tests 3 Total Cost $0.027 Response Time (avg) 5.51s
#367	GLM 5V Turbo none	Z.ai	0.5	0.5	$0.052	1/4	3.13s
Total Tests 4 Wrong Tests 3 Total Cost $0.052 Response Time (avg) 3.13s
#370	Owl Alpha medium	Openrouter	0.5	0.5	$0.000	1/4	3.97s
Total Tests 4 Wrong Tests 3 Total Cost $0.000 Response Time (avg) 3.97s
#377	Nemotron 3 Super none	NVIDIA	0.5	0.4	$0.016	1/4	4.46s
Total Tests 4 Wrong Tests 3 Total Cost $0.016 Response Time (avg) 4.46s
#378	KAT Coder AIR V2.5 default	Kwaipilot	0.5	0.4	$0.070	1/4	2.68s
Total Tests 4 Wrong Tests 3 Total Cost $0.070 Response Time (avg) 2.68s
#380	Granite 4.2 8B none	IBM Granite	0.5	0.4	$0.037	1/4	17.8s
Total Tests 4 Wrong Tests 3 Total Cost $0.037 Response Time (avg) 17.8s
#385	GLM 4.7 Flash medium	Z.ai	0.5	0.4	$0.193	1/4	15.0s
Total Tests 4 Wrong Tests 3 Total Cost $0.193 Response Time (avg) 15.0s
#390	Qwen3.5-9B medium	Qwen	0.5	0.4	$0.106	1/4	34.4s
Total Tests 4 Wrong Tests 3 Total Cost $0.106 Response Time (avg) 34.4s

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)