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
0.6
Mejor modelo
Claude Fable 5.2 1.0
514/514
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) |
|---|---|---|---|---|---|---|---|
| #9 | Gemini 3.7 Flash high | 1.0 | 1.0 | $0.528 | 1/1 | 78.5s | |
| #200 | Inkling medium | Thinkingmachines | 0.5 | 0.7 | $0.527 | 0/1 | 45.9s |
| #362 | ERNIE-Light-DT-1.0 none | Baidu | 0.5 | 0.6 | $0.524 | 0/1 | 49.9s |
| #139 | GLM 5.3 FlashX Legal high | Z.ai | 1.0 | 0.8 | $0.521 | 1/1 | 79.0s |
| #114 | Claude Haiku 5.5 max | Anthropic | 0.5 | 0.8 | $0.509 | 0/1 | 93.3s |
| #292 | Gemini 3.5 Flash minimal | 0.5 | 0.6 | $0.508 | 0/1 | 49.2s | |
| #280 | KAT-Coder-Pro V2.5 high | Kwaipilot | 0.3 | 0.6 | $0.506 | 0/1 | 1.52s |
| #177 | Muse Glimmer 30B high | Meta | 1.0 | 0.8 | $0.506 | 1/1 | 139.7s |
| #374 | Claude Opus 4.7 none | Anthropic | 0.0 | 0.5 | $0.505 | 0/0 | 0ms |
| #270 | Beam 1.0 501B A23B medium | Reflection | 0.3 | 0.7 | $0.499 | 0/1 | 31.6s |
| #169 | GLM 5.3 high | Z.ai | 1.0 | 0.8 | $0.495 | 1/1 | 40.7s |
| #148 | DeepSeek V4.1 Flash low | DeepSeek | 0.6 | 0.8 | $0.494 | 0/1 | 56.0s |
| #293 | ERNIE-Light-DT-1.0 low | Baidu | 0.6 | 0.6 | $0.489 | 0/1 | 96.9s |
| #367 | Kimi K2.6 none | Moonshot AI | 0.5 | 0.5 | $0.486 | 0/1 | 175.2s |
| #138 | GPT-5.6 Terra medium | OpenAI | 1.0 | 0.8 | $0.483 | 1/1 | 54.7s |