Anti-AI Tricks Model Ranking

AI BENCHY Category

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

Models Shown

Average Anti-AI Tricks Score

6.9

Best Model

Failure Reasons

With failure reason Wrong answer245 With failure reason Did not follow instructions30 With failure reason Extra formatting14 With failure reason API error13 With failure reason Timed out4 With failure reason No answer2

Rank	Model	Company	Anti-AI Tricks Score	Score	Tests Correct	Response Time (avg)
#63	GPT-5.3 Chat none	OpenAI	6.7	7.2	2/4	3.86s
#138	Ling-2.6-flash none	Inclusionai	6.8	5.0	2/4	11.8s
#81	Mercury 2 medium	Inception	6.9	6.6	2/4	1.12s
#84	Grok 4.20 Multi Agent Beta medium	X AI	6.9	6.6	2/4	3.46s
#91	GPT-5.5 none	OpenAI	6.9	6.4	2/4	1.31s
#107	Laguna Xs.2 medium	Poolside	6.9	5.8	2/4	2.68s
#60	Kimi K2.6 medium	Moonshot AI	7.0	7.2	2/4	11.6s
#54	GPT-5 Mini medium	OpenAI	7.1	7.3	2/4	13.9s
#59	GLM 5V Turbo medium	Z.ai	7.2	7.2	2/4	10.8s
#61	Gemini 3.1 Flash Lite low	Google	7.3	7.2	2/4	1.84s
#76	Kimi K2.5 medium	Moonshot AI	7.3	6.8	2/4	51.4s
#79	Hunter Alpha medium	OpenRouter	7.3	6.7	2/4	4.75s
#58	Gemini 3.1 Flash Lite Preview none	Google	7.5	7.2	2/4	1.04s
#90	Gemini 3.1 Flash Lite none	Google	7.5	6.4	2/4	1.07s
#130	MiniMax M2.7 medium	Minimax	7.9	5.3	2/4	40.3s

Anti-AI Tricks Ranking