Classement Programmation
Voyez quels modèles d'IA réussissent le mieux sur Programmation, lesquels restent fiables et où les écarts sont les plus marqués. Trier par: Tests corrects ↑.
289/289
Filtrer les modèles
Aucun modèle ne correspond à la recherche et aux filtres actuels.
| Rang | Modèle | Entreprise | Score Programmation | Score | Coût total | Tests corrects | Temps de réponse (moy.) |
|---|---|---|---|---|---|---|---|
| #195 | GPT-5.4 none | OpenAI | 5.5 | 5.8 | $0.397 | 1/3 | 1.62s |
| #196 | Solar Pro 4 none | Upstage | 5.5 | 5.8 | $0.006 | 1/3 | 2.61s |
| #201 | Ling-3.0-flash none | Inclusionai | 5.5 | 5.7 | $0.004 | 1/3 | 6.39s |
| #203 | Kimi K2.6 none | Moonshot AI | 5.5 | 5.7 | $0.230 | 1/3 | 82.6s |
| #207 | GLM 5V Turbo none | Z.ai | 5.5 | 5.6 | $0.052 | 1/3 | 3.13s |
| #208 | Owl Alpha medium | Openrouter | 5.4 | 5.6 | $0.000 | 1/3 | 18.7s |
| #210 | Mimo V2 PRO none | Xiaomi | 5.5 | 5.6 | $0.045 | 1/3 | 2.65s |
| #211 | Owl Alpha none | Openrouter | 5.6 | 5.6 | $0.000 | 1/3 | 36.9s |
| #214 | Qwen3.6 27B none | Qwen | 5.5 | 5.5 | $0.116 | 1/3 | 4.16s |
| #215 | Hy3 preview low | Tencent | 5.3 | 5.5 | $0.042 | 1/3 | 27.9s |
| #216 | Qwen3.8 27B none | Qwen | 5.5 | 5.5 | ~$0.006 | 1/3 | 1.19s |
| #219 | Laguna S 2.1 medium | Poolside | 5.3 | 5.4 | $0.053 | 1/3 | 159.0s |
| #223 | Kimi K2.5 none | Moonshot AI | 5.5 | 5.4 | $0.101 | 1/3 | 24.6s |
| #225 | Laguna S 2.1 high | Poolside | 5.3 | 5.4 | $0.114 | 1/3 | 271.4s |
| #231 | Qwen3.6 35B A3B none | Qwen | 5.5 | 5.3 | $0.060 | 1/3 | 8.77s |