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: Tests corrects ↑.
461/461
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.) |
|---|---|---|---|---|---|---|---|
| #32 | GPT-6.1 Terra xhigh | OpenAI | 0.3 | 0.9 | $0.789 | 0/1 | 39.9s |
| #33 | GPT-6.1 Terra low | OpenAI | 0.3 | 0.9 | $0.221 | 0/1 | 3.27s |
| #34 | Seed 2.1 Turbo low | Bytedance Seed | 0.3 | 0.9 | $1.645 | 0/1 | 171.9s |
| #35 | Muse Spark Open high | Meta | 0.3 | 0.9 | $1.782 | 0/1 | 330.1s |
| #36 | Claude Opus 5.5 medium | Anthropic | 0.3 | 0.9 | $1.804 | 0/1 | 27.7s |
| #37 | Muse Wonder medium | Meta | 0.5 | 0.9 | $3.397 | 0/1 | 16.3s |
| #38 | GPT-5.5 medium | OpenAI | 0.3 | 0.9 | $4.809 | 0/1 | 37.9s |
| #39 | Claude Sonnet 5.5 max | Anthropic | 0.3 | 0.9 | $8.557 | 0/1 | 47.0s |
| #40 | Qwen3.8 MAX medium | Qwen | 0.3 | 0.9 | $1.181 | 0/1 | 11.5s |
| #41 | DeepSeek V4.1 Flash 1017 low | DeepSeek | 0.3 | 0.9 | $0.355 | 0/1 | 33.8s |
| #42 | Qwen3.8 Max (0902) high | Qwen | 0.3 | 0.9 | $3.306 | 0/1 | 532.6s |
| #43 | GPT-5.3-Codex medium | OpenAI | 0.3 | 0.9 | $1.318 | 0/1 | 14.4s |
| #44 | Claude Haiku 5.5 xhigh | Anthropic | 0.3 | 0.9 | $0.140 | 0/1 | 4.79s |
| #45 | Muse Spark 1.3 high | Meta | 0.3 | 0.9 | $1.891 | 0/1 | 140.1s |
| #46 | Muse Wonder low | Meta | 0.3 | 0.9 | $2.637 | 0/1 | 8.23s |