Categoría AI BENCHY
Ranking de Trucos anti-IA
Mira qué modelos de IA rinden mejor en Trucos anti-IA, cuáles se mantienen fiables y dónde aparecen las mayores diferencias. Ordenar por: Pruebas correctas ↑.
169/169
Filtrar modelos
Ningún modelo coincide con la búsqueda y los filtros actuales.
| Rango | Modelo | Empresa | Puntuación de Trucos anti-IA | Puntuación | Costo total | Pruebas correctas | Tiempo de respuesta (promedio) |
|---|---|---|---|---|---|---|---|
| #108 | Owl Alpha medium | Openrouter | 4.8 | 5.8 | $0.000 | 1/4 | 3.97s |
| #111 | Kimi K2.6 none | Moonshot AI | 4.6 | 5.8 | $0.079 | 1/4 | 1.39s |
| #122 | Qwen3.5 Plus 2026-04-20 none | Qwen | 4.8 | 5.5 | $0.032 | 1/4 | 1.88s |
| #125 | Qwen3.5-122B-A10B none | Qwen | 4.8 | 5.3 | $0.020 | 1/4 | 1.59s |
| #133 | Mistral Small 4 medium | Mistral | 5.6 | 5.1 | $0.068 | 1/4 | 2.67s |
| #139 | GPT-4o-mini none | OpenAI | 4.8 | 5.0 | $0.006 | 1/4 | 1.34s |
| #141 | GLM 4.7 Flash none | Z.ai | 5.2 | 4.9 | $0.004 | 1/4 | 5.51s |
| #142 | Nemotron 3 Super none | NVIDIA | 4.8 | 4.9 | $0.007 | 1/4 | 4.46s |
| #155 | Grok 4.20 none | X AI | 4.8 | 4.4 | $0.057 | 1/4 | 501ms |
| #157 | GLM 4.7 Flash medium | Z.ai | 4.7 | 4.3 | $0.054 | 1/4 | 15.0s |
| #158 | Hy3 preview none | Tencent | 4.8 | 4.3 | $0.003 | 1/4 | 11.1s |
| #163 | Granite 4.1 8B none | IBM Granite | 4.9 | 4.0 | $0.003 | 1/4 | 844ms |
| #165 | Qwen3.5-9B medium | Qwen | 5.1 | 3.8 | $0.036 | 1/4 | 34.4s |
| #167 | Nemotron 3 Nano Omni 30b A3b Reasoning none | NVIDIA | 4.8 | 3.5 | $0.000 | 1/4 | 584ms |
| #16 | GPT-5 Mini medium | OpenAI | 7.1 | 8.5 | $0.159 | 2/4 | 13.9s |