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) |
|---|---|---|---|---|---|---|---|
| #83 | Muse Spark Open medium | Meta | 1.0 | 0.9 | $1.260 | 1/1 | 43.3s |
| #195 | Seed-2.0-Code medium | Bytedance Seed | 1.0 | 0.7 | $1.275 | 1/1 | 91.7s |
| #162 | Gemini 3.5 Flash medium | 0.3 | 0.8 | $1.316 | 0/1 | 84.5s | |
| #50 | GPT-5.3-Codex medium | OpenAI | 1.0 | 0.9 | $1.318 | 1/1 | 61.9s |
| #36 | Gemini 4 Hydrogen medium | 1.0 | 0.9 | $1.330 | 1/1 | 70.4s | |
| #173 | Grok 4.5 low | X AI | 0.5 | 0.8 | $1.345 | 0/1 | 61.5s |
| #105 | Qwen4 Max high | Qwen | 0.5 | 0.9 | $1.363 | 0/1 | 228.8s |
| #6 | GPT-6.1 Sol xhigh | OpenAI | 1.0 | 1.0 | $1.377 | 1/1 | 58.9s |
| #190 | Mistral Large 4 high | Mistral | 1.0 | 0.8 | $1.391 | 1/1 | 85.8s |
| #253 | Grok Build 0.1 medium | X AI | 0.3 | 0.7 | $1.419 | 0/1 | 69.0s |
| #112 | Claude Sonnet 5 medium | Anthropic | 1.0 | 0.9 | $1.438 | 1/1 | 69.3s |
| #191 | Seed-2.0-Code high | Bytedance Seed | 1.0 | 0.7 | $1.448 | 1/1 | 139.9s |
| #269 | Step 3.7 Flash high | Stepfun | 0.5 | 0.7 | $1.478 | 0/1 | 130.4s |
| #232 | Ember-1 low | Fireworks | 0.5 | 0.7 | $1.488 | 0/1 | 121.3s |
| #102 | Claude Sonnet 5.5 xhigh | Anthropic | 1.0 | 0.9 | $1.516 | 1/1 | 54.9s |