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: Coût total ↓.
514/514
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.) |
|---|---|---|---|---|---|---|---|
| #243 | Claude Sonnet 5.5 low | Anthropic | 1.0 | 0.7 | $0.909 | 1/1 | 46.6s |
| #1 | Gemini 3.6 Flash high | 1.0 | 1.0 | $0.900 | 1/1 | 65.6s | |
| #101 | Muse Spark 1.1 low | Meta | 1.0 | 0.9 | $0.885 | 1/1 | 42.2s |
| #87 | Muse Spark 1.2 low | Meta | 1.0 | 0.9 | $0.881 | 1/1 | 56.8s |
| #144 | Seed-2.0-Code low | Bytedance Seed | 1.0 | 0.8 | $0.881 | 1/1 | 90.2s |
| #16 | Gemini 3 Flash Preview medium | 1.0 | 1.0 | $0.876 | 1/1 | 59.2s | |
| #321 | Trinity Large Thinking medium | Arcee AI | 0.6 | 0.6 | $0.862 | 0/1 | 52.5s |
| #289 | Kimi K2.5 medium | Moonshot AI | 0.4 | 0.6 | $0.841 | 0/1 | 566.8s |
| #274 | Qwen3.6 35B A3B medium | Qwen | 0.6 | 0.7 | $0.834 | 0/1 | 88.5s |
| #161 | GLM 5.3 FlashX Legal max | Z.ai | 0.6 | 0.8 | $0.819 | 0/1 | 93.3s |
| #285 | Beam 1.0 501B A23B max | Reflection | 0.3 | 0.6 | $0.799 | 0/1 | 50.1s |
| #261 | GPT-5.6 Sol none | OpenAI | 0.5 | 0.7 | $0.795 | 0/1 | 58.3s |
| #350 | Trinity Large Thinking high | Arcee AI | 1.0 | 0.6 | $0.794 | 1/1 | 45.0s |
| #33 | GPT-6.1 Terra xhigh | OpenAI | 1.0 | 0.9 | $0.789 | 1/1 | 47.9s |
| #380 | Ember-1 none | Fireworks | 0.6 | 0.5 | $0.786 | 0/1 | 92.9s |