Categorie AI BENCHY
Clasament Combinat
Vezi ce modele AI se descurcă cel mai bine la Combinat, care rămân fiabile și unde apar cele mai mari diferențe. Sortează după: Teste corecte ↑.
| Rang | Model | Companie | Scor Combinat | Scor | Teste corecte | Timp de răspuns (mediu) |
|---|---|---|---|---|---|---|
| #5 | Gemini 3 Flash Preview low | 3.0 | 8.8 | 0/1 | 3.27s | |
| #12 | Gemini 3 PRO Preview medium | 3.0 | 8.4 | 0/1 | 10.4s | |
| #14 | Gemma 4 31B medium | 3.0 | 8.3 | 0/1 | 0ms | |
| #21 | Gemini 3 Flash Preview none | 4.7 | 8.1 | 0/1 | 3.56s | |
| #22 | Gemini 3.1 Flash Lite Preview low | 3.0 | 8.1 | 0/1 | 11.9s | |
| #23 | MiMo-V2-Pro medium | Xiaomi | 4.7 | 8.1 | 0/1 | 64.7s |
| #29 | Gemini 3.1 Flash Lite Preview none | 3.0 | 7.9 | 0/1 | 3.20s | |
| #31 | GLM 5V Turbo medium | Z.ai | 6.9 | 7.8 | 0/1 | 15.1s |
| #43 | Qwen3.5-35B-A3B medium | Qwen | 4.7 | 7.4 | 0/1 | 75.3s |
| #48 | Gemma 4 31B none | 3.0 | 6.9 | 0/1 | 0ms | |
| #49 | Qwen3.5 Plus 2026-02-15 none | Qwen | 3.0 | 6.8 | 0/1 | 6.65s |
| #50 | Hunter Alpha medium | OpenRouter | 4.7 | 6.7 | 0/1 | 30.5s |
| #53 | GLM 5 none | Z.ai | 3.0 | 6.6 | 0/1 | 4.98s |
| #55 | MiMo-V2-Omni none | Xiaomi | 3.0 | 6.5 | 0/1 | 2.47s |
| #56 | Grok 4.20 Multi Agent Beta medium | X AI | 3.0 | 6.4 | 0/1 | 0ms |