Catégorie AI BENCHY
Classement Combiné
Voyez quels modèles d'IA réussissent le mieux sur Combiné, lesquels restent fiables et où les écarts sont les plus marqués.
| Rang | Modèle | Entreprise | Score Combiné | Score | Tests corrects | Temps de réponse (moy.) |
|---|---|---|---|---|---|---|
| #98 | GLM 5 none | Z.ai | 3.0 | 6.1 | 0/1 | 4.98s |
| #100 | Grok Build 0.1 none | X AI | 3.0 | 6.0 | 0/1 | 0ms |
| #101 | Mimo V2 Omni none | Xiaomi | 3.0 | 6.0 | 0/1 | 5.96s |
| #102 | Gemma 4 26B A4B none | 3.0 | 6.0 | 0/1 | 30.5s | |
| #104 | Nemotron 3 Ultra 550b A55b none | NVIDIA | 3.0 | 6.0 | 0/1 | 4.79s |
| #106 | Grok 4.20 Beta none | X AI | 3.0 | 5.8 | 0/1 | 6.48s |
| #107 | Laguna Xs.2 medium | Poolside | 3.0 | 5.8 | 0/1 | 15.9s |
| #108 | Qwen3.5-Flash none | Qwen | 3.0 | 5.8 | 0/1 | 6.22s |
| #109 | GLM 5V Turbo none | Z.ai | 3.0 | 5.8 | 0/1 | 6.51s |
| #110 | Seed-2.0-Lite none | Bytedance Seed | 3.0 | 5.8 | 0/1 | 6.59s |
| #111 | Owl Alpha medium | Openrouter | 3.0 | 5.7 | 0/1 | 10.0s |
| #116 | Hunter Alpha none | OpenRouter | 3.0 | 5.7 | 0/1 | 15.2s |
| #117 | Qwen3.5-35B-A3B none | Qwen | 3.0 | 5.6 | 0/1 | 47.4s |
| #118 | Qwen3.6 27B none | Qwen | 3.0 | 5.6 | 0/1 | 9.95s |
| #119 | Cobuddy medium | Baidu | 3.0 | 5.6 | 0/1 | 47.4s |