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: Response Time (avg) ↑.
| Rank | Model | Company | Anti-AI Tricks Score | Score | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|
| #123 | MiMo-V2.5-Pro none | Xiaomi | 3.3 | 5.5 | 0/4 | 2.67s |
| #107 | Laguna Xs.2 medium | Poolside | 6.9 | 5.8 | 2/4 | 2.68s |
| #80 | Mimo V2 Omni medium | Xiaomi | 10.0 | 6.7 | 4/4 | 2.75s |
| #121 | Owl Alpha none | Openrouter | 3.4 | 5.5 | 0/4 | 2.78s |
| #118 | Qwen3.6 27B none | Qwen | 3.8 | 5.6 | 0/4 | 2.83s |
| #134 | GLM 5 Turbo none | Z.ai | 3.0 | 5.2 | 0/4 | 2.84s |
| #51 | Mimo V2 PRO medium | Xiaomi | 10.0 | 7.4 | 4/4 | 2.86s |
| #77 | Claude Sonnet 4.6 none | Anthropic | 4.8 | 6.8 | 1/4 | 2.94s |
| #52 | Claude Sonnet 4.6 medium | Anthropic | 6.5 | 7.4 | 2/4 | 2.98s |
| #109 | GLM 5V Turbo none | Z.ai | 4.8 | 5.8 | 1/4 | 3.13s |
| #13 | Grok 4.20 Beta medium | X AI | 8.7 | 8.5 | 3/4 | 3.16s |
| #43 | MiMo-V2.5-Pro medium | Xiaomi | 10.0 | 7.5 | 4/4 | 3.26s |
| #140 | Qwen3 Coder Next none | Qwen | 3.6 | 4.9 | 0/4 | 3.31s |
| #68 | Claude Opus 4.8 none | Anthropic | 6.5 | 7.0 | 2/4 | 3.40s |
| #24 | GPT-5.2 Chat none | OpenAI | 8.7 | 7.9 | 3/4 | 3.40s |