Categoría AI BENCHY
Ranking de Cultura general
Mira qué modelos de IA rinden mejor en Cultura general, cuáles se mantienen fiables y dónde aparecen las mayores diferencias. Ordenar por: Costo total ↑.
169/169
Filtrar modelos
Ningún modelo coincide con la búsqueda y los filtros actuales.
| Rango | Modelo | Empresa | Puntuación de Cultura general | Puntuación | Costo total | Pruebas correctas | Tiempo de respuesta (promedio) |
|---|---|---|---|---|---|---|---|
| #144 | Ring-2.6-1T none | Inclusionai | 3.0 | 4.8 | $0.026 | 0/1 | 133.6s |
| #101 | GLM 5 none | Z.ai | 3.0 | 6.0 | $0.027 | 0/1 | 3.62s |
| #23 | DeepSeek V4 Flash high | DeepSeek | 3.0 | 8.3 | $0.027 | 0/1 | 54.5s |
| #99 | Nemotron 3 Ultra 550b A55b none | NVIDIA | 3.0 | 6.1 | $0.027 | 0/1 | 1.83s |
| #118 | Kimi K2.5 none | Moonshot AI | 3.0 | 5.5 | $0.027 | 0/1 | 3.90s |
| #85 | Gemini 3.1 Flash Lite low | 3.0 | 6.4 | $0.028 | 0/1 | 1.46s | |
| #120 | Qwen3.6 27B none | Qwen | 3.0 | 5.5 | $0.028 | 0/1 | 4.03s |
| #128 | Qwen3.6 35B A3B none | Qwen | 3.0 | 5.2 | $0.031 | 0/1 | 414ms |
| #122 | Qwen3.5 Plus 2026-04-20 none | Qwen | 3.0 | 5.5 | $0.032 | 0/1 | 33.3s |
| #88 | Gemma 4 31B medium | 3.0 | 6.3 | $0.033 | 0/1 | 90.1s | |
| #72 | Ring-2.6-1T medium | Inclusionai | 3.0 | 6.8 | $0.033 | 0/1 | 113.9s |
| #58 | DeepSeek V4 Pro none | DeepSeek | 3.0 | 7.2 | $0.034 | 0/1 | 5.76s |
| #165 | Qwen3.5-9B medium | Qwen | 3.0 | 3.8 | $0.036 | 0/1 | 177.0s |
| #124 | GPT-5.4 Mini none | OpenAI | 3.0 | 5.3 | $0.038 | 0/1 | 1.33s |
| #62 | MiMo-V2-Flash medium | Xiaomi | 3.0 | 7.1 | $0.043 | 0/1 | 1.96s |