AI BENCHY Categorie
Anti-AI-trucs-ranglijst
Zie welke AI-modellen het best presteren op Anti-AI-trucs, welke betrouwbaar blijven en waar de grootste verschillen zitten. Sorteren op: Metriek ↑.
| Rang | Model | Bedrijf | Anti-AI-trucs-score | Score | Correcte tests | Responstijd (gem.) |
|---|---|---|---|---|---|---|
| #135 | Kimi K2.5 none | Moonshot AI | 3.6 | 5.2 | 0/4 | 6.24s |
| #153 | Qwen3.6 35B A3B none | Qwen | 3.6 | 4.6 | 0/4 | 2.10s |
| #101 | Mimo V2 Omni none | Xiaomi | 3.6 | 6.0 | 0/4 | 1.63s |
| #118 | Qwen3.6 27B none | Qwen | 3.8 | 5.6 | 0/4 | 2.83s |
| #112 | GLM 5.1 none | Z.ai | 4.0 | 5.7 | 0/4 | 2.11s |
| #106 | Grok 4.20 Beta none | X AI | 4.0 | 5.8 | 0/4 | 597ms |
| #124 | Kimi K2.6 none | Moonshot AI | 4.6 | 5.5 | 1/4 | 1.39s |
| #158 | GLM 4.7 Flash medium | Z.ai | 4.7 | 4.4 | 1/4 | 15.0s |
| #77 | Claude Sonnet 4.6 none | Anthropic | 4.8 | 6.8 | 1/4 | 2.94s |
| #95 | Qwen3.5 Plus 2026-02-15 none | Qwen | 4.8 | 6.3 | 1/4 | 1.91s |
| #98 | GLM 5 none | Z.ai | 4.8 | 6.1 | 1/4 | 2.37s |
| #109 | GLM 5V Turbo none | Z.ai | 4.8 | 5.8 | 1/4 | 3.13s |
| #111 | Owl Alpha medium | Openrouter | 4.8 | 5.7 | 1/4 | 3.97s |
| #114 | Qwen3.5 Plus 2026-04-20 none | Qwen | 4.8 | 5.7 | 1/4 | 1.88s |
| #115 | Qwen3.5-27B none | Qwen | 4.8 | 5.7 | 1/4 | 788ms |