Classement Tâches agentiques
Voyez quels modèles d'IA réussissent le mieux sur Tâches agentiques, lesquels restent fiables et où les écarts sont les plus marqués. Trier par: Tests corrects ↑.
380/380
Filtrer les modèles
Aucun modèle ne correspond à la recherche et aux filtres actuels.
| Rang | Modèle | Entreprise | Score Tâches agentiques | Score | Coût total | Tests corrects | Temps de réponse (moy.) |
|---|---|---|---|---|---|---|---|
| #51 | DeepSeek V4.1 Flash high | DeepSeek | 10.0 | 8.7 | $0.190 | 1/1 | 44.0s |
| #52 | DeepSeek V4.1 Flash medium | DeepSeek | 10.0 | 8.7 | $0.182 | 1/1 | 47.6s |
| #53 | Muse Spark 1.2 low | Meta | 10.0 | 8.7 | $0.881 | 1/1 | 56.8s |
| #54 | GPT-5.2 medium | OpenAI | 10.0 | 8.7 | $1.540 | 1/1 | 75.9s |
| #55 | Qwen3.8 27B high | Qwen | 10.0 | 8.7 | ~$0.298 | 1/1 | 132.3s |
| #56 | MiMo-V2.6-Pro medium | Xiaomi | 10.0 | 8.7 | $0.586 | 1/1 | 161.4s |
| #57 | Seed 2.1 Turbo medium | Bytedance Seed | 10.0 | 8.7 | $2.042 | 1/1 | 90.9s |
| #58 | GPT-6 Sol low | OpenAI | 10.0 | 8.7 | $0.477 | 1/1 | 48.4s |
| #59 | DeepSeek V4.1 Flash max | DeepSeek | 10.0 | 8.6 | $0.368 | 1/1 | 66.6s |
| #60 | Muse Spark 1.1 low | Meta | 10.0 | 8.6 | $0.885 | 1/1 | 42.2s |
| #61 | Claude Sonnet 5.5 xhigh | Anthropic | 10.0 | 8.6 | $1.516 | 1/1 | 54.9s |
| #62 | Claude Sonnet 5.5 high | Anthropic | 10.0 | 8.6 | $1.175 | 1/1 | 51.5s |
| #65 | Muse Spark 1.3 low | Meta | 10.0 | 8.5 | $0.911 | 1/1 | 55.1s |
| #66 | Claude Sonnet 5 medium | Anthropic | 10.0 | 8.5 | $1.438 | 1/1 | 69.3s |
| #68 | Qwen3.8 2.4T A95B low | Qwen | 10.0 | 8.4 | $3.172 | 1/1 | 151.8s |