AI BENCHY Categoriefouten
Anti-AI-trucs: Extra opmaak
Anti-AI-trucs
Extra opmaak
Zie welke AI-modellen op Anti-AI-trucs het meest kans hebben op Extra opmaak, zodat je zwakke punten sneller ziet.
| Rang | Model | Bedrijf | Extra opmaak-aantal | Categoriescore | Correcte tests | Responstijd (gem.) |
|---|---|---|---|---|---|---|
| #37 | Claude Opus 4.6 medium | Anthropic | 2 | 6.4 | 2/4 | 7.45s |
| #42 | Claude Sonnet 4.6 none | Anthropic | 2 | 4.8 | 1/4 | 2.94s |
| #64 | DeepSeek V3.2 none | DeepSeek | 2 | 3.2 | 0/4 | 7.63s |
| #10 | Qwen3.5-27B medium | Qwen | 1 | 8.7 | 3/4 | 19.8s |
| #26 | Claude Sonnet 4.6 medium | Anthropic | 1 | 6.5 | 2/4 | 2.98s |
| #41 | MiMo-V2-Flash medium | Xiaomi | 1 | 8.1 | 3/4 | 15.8s |
| #56 | Grok 4.20 Multi Agent Beta medium | X AI | 1 | 6.9 | 2/4 | 3.46s |
| #87 | Qwen3 Coder Next none | Qwen | 1 | 3.6 | 0/4 | 3.31s |