Categorie AI BENCHY
Clasament Programare
Vezi ce modele AI se descurcă cel mai bine la Programare, care rămân fiabile și unde apar cele mai mari diferențe. Sortează după: Metrică ↑.
| Rang | Model | Companie | Scor Programare | Scor | Teste corecte | Timp de răspuns (mediu) |
|---|---|---|---|---|---|---|
| #54 | GLM 5.1 medium | Z.ai | 4.7 | 7.4 | 0/2 | 145.6s |
| #131 | Elephant Alpha none | Openrouter | 4.7 | 5.2 | 0/2 | 1.39s |
| #132 | DeepSeek V4 Flash none | DeepSeek | 4.8 | 5.1 | 0/2 | 24.5s |
| #89 | Qwen3.5 Plus 2026-02-15 none | Qwen | 4.9 | 6.4 | 0/2 | 2.54s |
| #144 | MiMo-V2-Flash none | Xiaomi | 4.9 | 4.7 | 0/2 | 2.04s |
| #140 | Trinity Large Preview none | Arcee AI | 4.9 | 4.8 | 0/1 | 14.3s |
| #113 | GLM 4.7 Flash none | Z.ai | 5.0 | 5.6 | 0/2 | 3.35s |
| #115 | MiMo-V2.5-Pro none | Xiaomi | 5.0 | 5.6 | 0/2 | 1.80s |
| #93 | MiMo-V2-Omni none | Xiaomi | 5.1 | 6.2 | 0/2 | 2.75s |
| #43 | Qwen3.6 Flash medium | Qwen | 5.1 | 7.6 | 0/2 | 51.9s |
| #121 | Mistral Small 4 medium | Mistral | 5.1 | 5.4 | 0/2 | 44.8s |
| #153 | Granite 4.1 8B none | IBM Granite | 5.2 | 4.1 | 0/2 | 706ms |
| #150 | Grok 4.1 Fast none | X AI | 5.3 | 4.4 | 0/1 | 1.79s |
| #133 | Qwen3 Coder Next none | Qwen | 5.4 | 5.1 | 0/2 | 2.01s |
| #48 | Qwen3.5 Plus 2026-04-20 medium | Qwen | 5.4 | 7.6 | 1/2 | 137.5s |