AI BENCHY Categorie
Domeinspecifiek-ranglijst
Zie welke AI-modellen het best presteren op Domeinspecifiek, welke betrouwbaar blijven en waar de grootste verschillen zitten. Sorteren op: Metriek ↑.
| Rang | Model | Bedrijf | Domeinspecifiek-score | Score | Correcte tests | Responstijd (gem.) |
|---|---|---|---|---|---|---|
| #23 | GLM 5 Turbo medium | Z.ai | 2.9 | 8.0 | 0/3 | 71.1s |
| #37 | Gemma 4 26B A4B medium | 2.9 | 7.6 | 0/3 | 23.6s | |
| #72 | DeepSeek V3.2 medium | DeepSeek | 2.9 | 7.0 | 0/3 | 24.3s |
| #99 | gpt-oss-120b medium | OpenAI | 2.9 | 6.1 | 0/3 | 50.9s |
| #105 | Nemotron 3 Super medium | NVIDIA | 2.9 | 5.8 | 0/3 | 16.2s |
| #119 | Cobuddy medium | Baidu | 2.9 | 5.6 | 0/3 | 128.2s |
| #129 | MiniMax M2.5 medium | Minimax | 2.9 | 5.3 | 0/3 | 237.3s |
| #148 | GPT-5.4 Nano none | OpenAI | 2.9 | 4.7 | 0/3 | 926ms |
| #14 | Qwen3.6 Max Preview medium | Qwen | 2.9 | 8.5 | 0/3 | 95.9s |
| #26 | Qwen3.6 Plus medium | Qwen | 2.9 | 7.9 | 0/3 | 29.6s |
| #29 | Qwen3.5-122B-A10B medium | Qwen | 2.9 | 7.8 | 0/3 | 63.4s |
| #36 | Qwen3.5 Plus 2026-04-20 medium | Qwen | 2.9 | 7.6 | 0/3 | 53.1s |
| #44 | Gemini 3.1 Flash Lite medium | 2.9 | 7.5 | 0/3 | 3.16s | |
| #52 | Claude Sonnet 4.6 medium | Anthropic | 2.9 | 7.4 | 0/3 | 0ms |
| #78 | Qwen3.6 27B medium | Qwen | 2.9 | 6.8 | 0/3 | 73.4s |