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
Ernie 5.5 Flash Preview 0.6
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) |
|---|---|---|---|---|---|---|---|
| #477 | HeyGen Decision default | Heygen | 0.0 | 0.3 | $0.029 | 0/0 | 0ms |
| #336 | gpt-oss-120b medium | OpenAI | 0.5 | 0.6 | $0.030 | 0/1 | 203.9s |
| #371 | Gemma 4 26B A4B none | 0.5 | 0.5 | $0.031 | 0/1 | 75.8s | |
| #357 | Gemma 4 31B none | 0.4 | 0.6 | $0.031 | 0/1 | 44.7s | |
| #185 | GPT-6 Luna low | OpenAI | 1.0 | 0.8 | $0.033 | 1/1 | 51.0s |
| #456 | Laguna M.1 medium | Poolside | 0.0 | 0.4 | $0.033 | 0/0 | 0ms |
| #443 | Mercury 2 none | Inception | 0.3 | 0.4 | $0.033 | 0/1 | 9.00s |
| #291 | Mercury 2.5 medium | Inception | 0.5 | 0.6 | $0.034 | 0/1 | 107.9s |
| #383 | Granite 4.2 8B low | IBM Granite | 0.6 | 0.5 | $0.036 | 0/1 | 142.7s |
| #441 | Granite 4.2 8B none | IBM Granite | 0.5 | 0.4 | $0.037 | 0/1 | 49.2s |
| #263 | GLM 5.3 Flash low | Z.ai | 1.0 | 0.7 | $0.038 | 1/1 | 59.7s |
| #248 | Mercury 2.5 Preview medium | Inception | 0.4 | 0.7 | $0.039 | 0/1 | 74.6s |
| #275 | Mercury 2.5 Preview high | Inception | 0.6 | 0.6 | $0.040 | 0/1 | 86.8s |
| #365 | Nemotron 3.5 Super VL none | NVIDIA | 0.5 | 0.6 | $0.040 | 0/1 | 71.1s |
| #414 | Qwen3.5-9B none | Qwen | 0.4 | 0.5 | $0.041 | 0/1 | 433.0s |