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

6.7

Best Model

Failure Reasons

With failure reason Wrong answer165 With failure reason Did not follow instructions17 With failure reason Extra formatting11 With failure reason Timed out4 With failure reason No answer1

Rank	Model	Company	Anti-AI Tricks Score	Score	Tests Correct	Response Time (avg)
#63	Qwen3.5-35B-A3B none	Qwen	3.4	6.1	0/4	1.43s
#69	Kimi K2.6 none	Moonshot AI	4.6	5.8	1/4	1.39s
#89	GPT-4o-mini none	OpenAI	4.8	4.9	1/4	1.34s
#59	Qwen3.5-Flash none	Qwen	3.5	6.2	0/4	1.32s
#60	Gemma 4 26B A4B none	Google	8.3	6.2	3/4	1.28s
#21	Gemini 3 Flash Preview none	Google	8.3	8.1	3/4	1.25s
#66	GPT-5.4 none	OpenAI	3.2	5.9	0/4	1.21s
#94	MiMo-V2-Flash none	Xiaomi	3.2	4.5	0/4	1.19s
#81	Elephant medium	Openrouter	6.6	5.2	2/4	1.19s
#96	GPT-5.4 Nano none	OpenAI	3.5	4.5	0/4	1.18s
#54	Mercury 2 medium	Inception	6.9	6.5	2/4	1.12s
#55	MiMo-V2-Omni none	Xiaomi	4.8	6.5	1/4	1.10s
#95	Grok 4.1 Fast none	X AI	3.2	4.5	0/4	1.07s
#29	Gemini 3.1 Flash Lite Preview none	Google	7.5	7.9	2/4	1.04s
#85	Elephant none	Openrouter	6.6	5.2	2/4	963ms

←

1 2 3 4 5 6 7

→

Anti-AI Tricks Ranking