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) |
|---|---|---|---|---|---|---|
| #40 | Qwen3.5-122B-A10B medium | Qwen | 4.1 | 7.7 | 0/2 | 119.6s |
| #47 | Qwen3.5-Flash medium | Qwen | 4.1 | 7.6 | 0/2 | 54.2s |
| #70 | MiMo-V2-Flash medium | Xiaomi | 4.1 | 7.1 | 0/2 | 7.20s |
| #92 | Gemma 4 26B A4B none | 4.1 | 6.2 | 0/2 | 3.83s | |
| #142 | Qwen3 Coder Next medium | Qwen | 4.1 | 4.7 | 0/2 | 1.17s |
| #35 | Qwen3.6 Plus medium | Qwen | 4.1 | 7.8 | 0/2 | 201.7s |
| #108 | Cobuddy medium | Baidu | 4.1 | 5.8 | 0/2 | 79.2s |
| #69 | Qwen3.6 Max Preview none | Qwen | 4.2 | 7.1 | 0/2 | 3.06s |
| #102 | GLM 5.1 none | Z.ai | 4.3 | 5.8 | 0/2 | 6.33s |
| #62 | Laguna M.1 medium | Poolside | 4.3 | 7.3 | 0/1 | 35.6s |
| #119 | gpt-oss-120b none | OpenAI | 4.3 | 5.4 | 0/1 | 9.57s |
| #103 | Qwen3.5 Plus 2026-04-20 none | Qwen | 4.4 | 5.8 | 0/2 | 2.08s |
| #127 | GLM 5 Turbo none | Z.ai | 4.4 | 5.3 | 0/2 | 2.58s |
| #143 | Qwen3.5-9B none | Qwen | 4.4 | 4.7 | 0/2 | 5.39s |
| #91 | GLM 5 none | Z.ai | 4.6 | 6.3 | 0/2 | 5.18s |