AI BENCHY Categorie
Programmeren-ranglijst
Zie welke AI-modellen het best presteren op Programmeren, welke betrouwbaar blijven en waar de grootste verschillen zitten. Sorteren op: Correcte tests ↑.
| Rang | Model | Bedrijf | Programmeren-score | Score | Correcte tests | Responstijd (gem.) |
|---|---|---|---|---|---|---|
| #10 | Gemini 3 PRO Preview medium | 3.0 | 8.4 | 0/1 | 0ms | |
| #12 | Gemma 4 31B medium | 4.7 | 8.3 | 0/1 | 71.0s | |
| #17 | Qwen3.5-122B-A10B medium | Qwen | 4.7 | 8.1 | 0/1 | 71.0s |
| #18 | Qwen3.6 Plus medium | Qwen | 3.0 | 8.1 | 0/1 | 0ms |
| #22 | Gemma 4 26B A4B medium | 2.8 | 8.0 | 0/1 | 147.5s | |
| #25 | DeepSeek V3.2 medium | DeepSeek | 4.7 | 8.0 | 0/1 | 180.9s |
| #30 | Qwen3.5-Flash medium | Qwen | 4.7 | 7.8 | 0/1 | 45.7s |
| #31 | GLM 5.1 medium | Z.ai | 4.7 | 7.8 | 0/1 | 118.5s |
| #32 | MiMo-V2-Omni medium | Xiaomi | 4.0 | 7.7 | 0/1 | 68.5s |
| #38 | MiMo-V2-Flash medium | Xiaomi | 4.7 | 7.5 | 0/1 | 13.0s |
| #43 | Kimi K2.5 medium | Moonshot AI | 4.7 | 7.0 | 0/1 | 150.8s |
| #44 | Grok 4.20 medium | X AI | 4.3 | 7.0 | 0/1 | 24.3s |
| #46 | Qwen3.5 Plus 2026-02-15 none | Qwen | 6.3 | 6.8 | 0/1 | 3.63s |
| #47 | Hunter Alpha medium | OpenRouter | 3.0 | 6.7 | 0/1 | 0ms |
| #48 | Nemotron 3 Super medium | NVIDIA | 3.0 | 6.7 | 0/1 | 0ms |