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.) |
|---|---|---|---|---|---|---|
| #1 | Gemini 3 Flash Preview medium | 10.0 | 10.0 | 3/3 | 21.1s | |
| #2 | Gemini 3.1 Pro Preview medium | 7.7 | 9.6 | 2/3 | 32.7s | |
| #3 | Claude Opus 4.7 medium | Anthropic | 7.7 | 9.2 | 2/3 | 1.17s |
| #4 | Claude Opus 4.7 none | Anthropic | 7.7 | 9.2 | 2/3 | 1.19s |
| #14 | Gemma 4 31B medium | 7.7 | 8.3 | 2/3 | 38.5s | |
| #21 | Gemini 3 Flash Preview none | 7.7 | 8.1 | 2/3 | 963ms | |
| #42 | Claude Sonnet 4.6 none | Anthropic | 7.7 | 7.4 | 2/3 | 3.54s |
| #48 | Gemma 4 31B none | 7.7 | 6.9 | 2/3 | 3.22s | |
| #59 | Qwen3.5-Flash none | Qwen | 7.7 | 6.2 | 2/3 | 905ms |
| #63 | Qwen3.5-35B-A3B none | Qwen | 7.7 | 6.1 | 2/3 | 485ms |
| #74 | GLM 4.7 Flash none | Z.ai | 7.7 | 5.6 | 2/3 | 744ms |
| #6 | Seed-2.0-Lite medium | Bytedance Seed | 5.9 | 8.6 | 1/3 | 88.7s |
| #7 | GPT-5.3-Codex medium | OpenAI | 5.9 | 8.6 | 1/3 | 64.3s |
| #15 | Gemini 2.5 Flash medium | 5.9 | 8.2 | 1/3 | 37.3s | |
| #38 | GPT-5.4 Nano medium | OpenAI | 5.9 | 7.6 | 1/3 | 38.2s |