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.) |
|---|---|---|---|---|---|---|
| #140 | Qwen3 Coder Next none | Qwen | 3.0 | 4.9 | 0/1 | 45.1s |
| #141 | Nemotron 3 Super none | NVIDIA | 3.0 | 4.9 | 0/1 | 16.4s |
| #142 | Mistral Small 4 none | Mistral | 3.0 | 4.9 | 0/1 | 1.72s |
| #143 | MiMo-V2.5 none | Xiaomi | 3.0 | 4.9 | 0/1 | 2.36s |
| #144 | GPT-5.4 Mini none | OpenAI | 3.0 | 4.9 | 0/1 | 2.52s |
| #145 | Laguna M.1 none | Poolside | 3.0 | 4.8 | 0/1 | 4.32s |
| #146 | Laguna Xs.2 none | Poolside | 3.0 | 4.8 | 0/1 | 2.01s |
| #147 | GPT-4o-mini none | OpenAI | 3.0 | 4.8 | 0/1 | 7.58s |
| #148 | GPT-5.4 Nano none | OpenAI | 3.0 | 4.7 | 0/1 | 3.84s |
| #149 | Nemotron 3 Nano Omni 30b A3b Reasoning medium | NVIDIA | 3.0 | 4.6 | 0/1 | 0ms |
| #150 | Qwen3 Coder Next medium | Qwen | 3.0 | 4.6 | 0/1 | 4.28s |
| #151 | Trinity Large Preview none | Arcee AI | 3.0 | 4.6 | 0/1 | 8.91s |
| #152 | MiMo-V2-Flash none | Xiaomi | 3.0 | 4.6 | 0/1 | 2.87s |
| #153 | Qwen3.6 35B A3B none | Qwen | 3.0 | 4.6 | 0/1 | 0ms |
| #154 | Qwen3.5-9B none | Qwen | 3.0 | 4.6 | 0/1 | 5.91s |