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)
#87	Gemini 3.1 Flash Lite minimal	Google	8.3	6.4	3/4	1.10s
#89	Hy3 preview low	Tencent	8.3	6.4	3/4	9.32s
#93	Qwen3.6 Plus Preview medium	Qwen	8.3	6.3	3/4	11.7s
#102	Gemma 4 26B A4B none	Google	8.3	6.0	3/4	1.28s
#105	Nemotron 3 Super medium	NVIDIA	8.3	5.8	3/4	7.85s
#28	Gemini 2.5 Flash medium	Google	8.4	7.8	3/4	6.30s
#45	GPT-5.4 Mini medium	OpenAI	8.6	7.5	3/4	4.05s
#53	Gemini 3.1 Flash Lite high	Google	8.7	7.3	3/4	37.2s
#13	Grok 4.20 Beta medium	X AI	8.7	8.5	3/4	3.16s
#15	GPT-5.3-Codex medium	OpenAI	8.7	8.4	3/4	4.16s
#22	Step 3.7 Flash medium	Stepfun	8.7	8.0	3/4	9.65s
#24	GPT-5.2 Chat none	OpenAI	8.7	7.9	3/4	3.40s
#30	Qwen3.5-27B medium	Qwen	8.7	7.8	3/4	19.8s
#57	Step 3.7 Flash low	Stepfun	8.7	7.3	3/4	4.02s
#86	Grok 4.1 Fast medium	X AI	8.7	6.5	3/4	3.81s

Anti-AI Tricks Ranking