Classement Culture générale
Voyez quels modèles d'IA réussissent le mieux sur Culture générale, lesquels restent fiables et où les écarts sont les plus marqués. Trier par: Temps de réponse (moy.) ↓.
343/343
Filtrer les modèles
Aucun modèle ne correspond à la recherche et aux filtres actuels.
| Rang | Modèle | Entreprise | Score Culture générale | Score | Coût total | Tests corrects | Temps de réponse (moy.) |
|---|---|---|---|---|---|---|---|
| #45 | Muse Spark 1.2 high | Meta | 3.0 | 8.7 | $1.771 | 0/1 | 15.0s |
| #321 | Granite 4.2 8B none | IBM Granite | 3.0 | 4.3 | $0.037 | 0/1 | 14.6s |
| #32 | GPT-5.3-Codex medium | OpenAI | 2.8 | 8.9 | $0.988 | 0/1 | 14.4s |
| #184 | Inkling Small medium | Thinkingmachines | 3.0 | 6.6 | $0.113 | 0/1 | 14.2s |
| #20 | Claude Opus 5 high | Anthropic | 3.0 | 9.2 | $3.070 | 0/1 | 14.1s |
| #5 | GPT-6 Astra xhigh | OpenAI | 10.0 | 9.9 | $5.156 | 1/1 | 14.1s |
| #58 | Grok 4.5 low | X AI | 3.0 | 8.4 | $0.945 | 0/1 | 14.0s |
| #51 | GPT-5.4 medium | OpenAI | 3.0 | 8.5 | $1.560 | 0/1 | 14.0s |
| #23 | Qwen3.8 Max (0902) low | Qwen | 3.0 | 9.1 | $0.664 | 0/1 | 13.3s |
| #46 | Muse Spark 1.2 medium | Meta | 3.0 | 8.6 | $1.339 | 0/1 | 12.8s |
| #86 | Qwen3.8 27B low | Qwen | 3.0 | 7.9 | ~$0.071 | 0/1 | 12.6s |
| #170 | MiMo-V2.5-Pro medium | Xiaomi | 3.0 | 6.8 | $0.221 | 0/1 | 12.5s |
| #50 | Qwen3.8 Max low | Qwen | 3.0 | 8.6 | $0.702 | 0/1 | 12.4s |
| #132 | GLM 5.3 Flash high | Z.ai | 3.0 | 7.3 | $0.057 | 0/1 | 11.5s |
| #29 | Qwen3.8 Max medium | Qwen | 3.0 | 9.0 | $0.771 | 0/1 | 11.5s |