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: Response Time (avg) ↓.

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)
#2	Gemini 3.5 Flash high	Google	10.0	9.6	4/4	2.57s
#20	Gemini 3.5 Flash none	Google	10.0	8.1	4/4	2.53s
#3	Gemini 3.5 Flash low	Google	10.0	9.4	4/4	2.52s
#110	Seed-2.0-Lite none	Bytedance Seed	3.0	5.8	0/4	2.43s
#44	Gemini 3.1 Flash Lite medium	Google	9.1	7.5	3/4	2.39s
#98	GLM 5 none	Z.ai	4.8	6.1	1/4	2.37s
#104	Nemotron 3 Ultra 550b A55b none	NVIDIA	3.5	6.0	0/4	2.35s
#40	Gemini 3.1 Flash Lite Preview medium	Google	9.1	7.5	3/4	2.33s
#143	MiMo-V2.5 none	Xiaomi	3.5	4.9	0/4	2.19s
#8	Claude Opus 4.7 none	Anthropic	8.3	8.9	3/4	2.12s
#50	Gemini 3.1 Flash Lite Preview low	Google	8.3	7.4	3/4	2.12s
#112	GLM 5.1 none	Z.ai	4.0	5.7	0/4	2.11s
#153	Qwen3.6 35B A3B none	Qwen	3.6	4.6	0/4	2.10s
#7	Gemini 3.5 Flash medium	Google	10.0	9.0	4/4	2.09s
#151	Trinity Large Preview none	Arcee AI	3.1	4.6	0/4	2.07s

Anti-AI Tricks Ranking