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 ↓.
Modelos mostrados
15
Promedio de Puntuación de Trucos anti-IA
6.7
Mejor modelo
Gemini 3 Flash Preview 10.0| Rango | Modelo | Empresa | Puntuación de Trucos anti-IA | Puntuación | Pruebas correctas | Tiempo de respuesta (promedio) |
|---|---|---|---|---|---|---|
| #27 | MiMo-V2.5-Pro medium | Xiaomi | 10.0 | 8.1 | 4/4 | 2.95s |
| #28 | MiMo-V2-Pro medium | Xiaomi | 10.0 | 8.1 | 4/4 | 3.06s |
| #29 | HY3 Preview medium | Tencent | 10.0 | 8.1 | 4/4 | 6.59s |
| #30 | Gemma 4 26B A4B medium | 10.0 | 8.0 | 4/4 | 6.20s | |
| #36 | Step 3.5 Flash medium | Stepfun | 10.0 | 7.9 | 4/4 | 13.6s |
| #39 | Qwen3.5-Flash medium | Qwen | 10.0 | 7.8 | 4/4 | 59.1s |
| #40 | GLM 5.1 medium | Z.ai | 10.0 | 7.8 | 4/4 | 8.31s |
| #41 | MiMo-V2.5 medium | Xiaomi | 10.0 | 7.8 | 4/4 | 1.98s |
| #43 | MiMo-V2-Omni medium | Xiaomi | 10.0 | 7.7 | 4/4 | 2.11s |
| #51 | Qwen3.5-35B-A3B medium | Qwen | 10.0 | 7.4 | 4/4 | 21.1s |
| #61 | Nemotron 3 Super medium | NVIDIA | 10.0 | 6.7 | 4/4 | 10.1s |
| #3 | Claude Opus 4.7 medium | Anthropic | 8.3 | 9.2 | 3/4 | 1.85s |
| #4 | Claude Opus 4.7 none | Anthropic | 8.3 | 9.2 | 3/4 | 2.12s |
| #8 | Seed-2.0-Lite medium | Bytedance Seed | 8.3 | 8.6 | 3/4 | 18.0s |
| #9 | GPT-5.3-Codex medium | OpenAI | 8.7 | 8.6 | 3/4 | 4.16s |