Ranking de Tareas de agentes
Mira qué modelos de IA rinden mejor en Tareas de agentes, cuáles se mantienen fiables y dónde aparecen las mayores diferencias. Ordenar por: Costo total ↓.
Modelos mostrados
15
Promedio de Puntuación de Tareas de agentes
5.8
Mejor modelo
Claude Sonnet 5.5 10.0
380/380
Filtrar modelos
Ningún modelo coincide con la búsqueda y los filtros actuales.
| Rango | Modelo | Empresa | Puntuación de Tareas de agentes | Puntuación | Costo total | Pruebas correctas | Tiempo de respuesta (promedio) |
|---|---|---|---|---|---|---|---|
| #18 | GPT-6 Sol medium | OpenAI | 10.0 | 9.5 | $0.703 | 1/1 | 51.5s |
| #222 | Trinity Large Thinking low | Arcee AI | 7.4 | 6.3 | $0.700 | 0/1 | 63.2s |
| #260 | GPT-5.4 none | OpenAI | 5.0 | 5.6 | $0.690 | 0/1 | 43.7s |
| #311 | Mimo V2 Omni medium | Xiaomi | 0.0 | 4.9 | $0.683 | 0/0 | 0ms |
| #237 | Claude Sonnet 4.6 none | Anthropic | 0.0 | 6.0 | $0.661 | 0/0 | 0ms |
| #253 | Trinity Large Thinking high | Arcee AI | 10.0 | 5.7 | $0.645 | 1/1 | 45.0s |
| #95 | GPT-5.6 Terra low | OpenAI | 10.0 | 7.9 | $0.645 | 1/1 | 54.6s |
| #135 | Gemini 2.5 Flash medium | 3.0 | 7.3 | $0.644 | 0/1 | 6.54s | |
| #112 | Muse Glimmer 30B high | Meta | 10.0 | 7.7 | $0.625 | 1/1 | 139.7s |
| #41 | Gemini 3.5 Flash Lite high | 10.0 | 9.0 | $0.624 | 1/1 | 53.1s | |
| #97 | GLM 5.3 FlashX max | Z.ai | 6.1 | 7.9 | $0.623 | 0/1 | 104.8s |
| #105 | GLM 5.3 high | Z.ai | 10.0 | 7.8 | $0.610 | 1/1 | 40.7s |
| #13 | GPT-5.6 Sol low | OpenAI | 10.0 | 9.6 | $0.609 | 1/1 | 57.1s |
| #43 | Gemini 3.6 Flash low | 10.0 | 9.0 | $0.607 | 1/1 | 48.5s | |
| #205 | Kimi K2.5 medium | Moonshot AI | 3.9 | 6.4 | $0.603 | 0/1 | 566.8s |