AI BENCHY Categorie
Domeinspecifiek-ranglijst
Zie welke AI-modellen het best presteren op Domeinspecifiek, welke betrouwbaar blijven en waar de grootste verschillen zitten.
| Rang | Model | Bedrijf | Domeinspecifiek-score | Score | Correcte tests | Responstijd (gem.) |
|---|---|---|---|---|---|---|
| #60 | Gemma 4 26B A4B none | 3.6 | 6.2 | 0/3 | 2.49s | |
| #61 | Seed-2.0-Lite none | Bytedance Seed | 3.6 | 6.2 | 0/3 | 1.33s |
| #64 | DeepSeek V3.2 none | DeepSeek | 3.6 | 6.1 | 0/3 | 1.61s |
| #88 | Nemotron 3 Super none | NVIDIA | 3.6 | 5.1 | 0/3 | 6.23s |
| #97 | Qwen3.5-9B medium | Qwen | 3.6 | 4.4 | 0/3 | 137.7s |
| #13 | GLM 5 medium | Z.ai | 3.5 | 8.4 | 0/3 | 0ms |
| #36 | GPT-5.3 Chat none | OpenAI | 3.5 | 7.7 | 0/3 | 13.0s |
| #46 | Kimi K2.5 medium | Moonshot AI | 3.5 | 7.0 | 0/3 | 137.3s |
| #86 | GPT-5.4 Mini none | OpenAI | 3.5 | 5.1 | 0/3 | 937ms |
| #93 | GLM 4.7 Flash medium | Z.ai | 3.5 | 4.6 | 0/3 | 174.6s |
| #9 | Qwen3.6 Plus Preview medium | Qwen | 3.0 | 8.5 | 0/3 | 22.1s |
| #17 | Gemini 3.1 Flash Lite Preview medium | 3.0 | 8.2 | 0/3 | 4.21s | |
| #35 | MiMo-V2-Omni medium | Xiaomi | 3.0 | 7.7 | 0/3 | 55.1s |
| #37 | Claude Opus 4.6 medium | Anthropic | 3.0 | 7.6 | 0/3 | 83.4s |
| #39 | Seed-2.0-Mini medium | Bytedance Seed | 3.0 | 7.5 | 0/3 | 0ms |