AI BENCHY Category
Anti-AI Tricks Ranking
See which AI models perform best on Anti-AI Tricks, which ones stay reliable, and where the biggest gaps appear. Sort by: Metric ↑.
| Rank | Model | Company | Anti-AI Tricks Score | Score | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|
| #85 | Elephant none | Openrouter | 6.6 | 5.2 | 2/4 | 963ms |
| #84 | gpt-oss-120b none | OpenAI | 6.6 | 5.2 | 2/4 | 6.03s |
| #68 | gpt-oss-120b medium | OpenAI | 6.7 | 5.8 | 2/4 | 10.2s |
| #36 | GPT-5.3 Chat none | OpenAI | 6.7 | 7.7 | 2/4 | 3.86s |
| #54 | Mercury 2 medium | Inception | 6.9 | 6.5 | 2/4 | 1.12s |
| #56 | Grok 4.20 Multi Agent Beta medium | X AI | 6.9 | 6.4 | 2/4 | 3.46s |
| #34 | Kimi K2.6 medium | Moonshot AI | 7.0 | 7.7 | 2/4 | 11.6s |
| #45 | GPT-5 Mini medium | OpenAI | 7.1 | 7.0 | 2/4 | 13.9s |
| #31 | GLM 5V Turbo medium | Z.ai | 7.2 | 7.8 | 2/4 | 10.8s |
| #46 | Kimi K2.5 medium | Moonshot AI | 7.3 | 7.0 | 2/4 | 51.4s |
| #50 | Hunter Alpha medium | OpenRouter | 7.3 | 6.7 | 2/4 | 4.75s |
| #29 | Gemini 3.1 Flash Lite Preview none | 7.5 | 7.9 | 2/4 | 1.04s | |
| #80 | MiniMax M2.7 medium | Minimax | 7.9 | 5.3 | 2/4 | 40.3s |
| #71 | MiniMax M2.5 medium | Minimax | 7.9 | 5.7 | 2/4 | 20.8s |
| #41 | MiMo-V2-Flash medium | Xiaomi | 8.1 | 7.5 | 3/4 | 15.8s |