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 ↑.
| Rango | Modelo | Empresa | Puntuación de Trucos anti-IA | Puntuación | Pruebas correctas | Tiempo de respuesta (promedio) |
|---|---|---|---|---|---|---|
| #97 | Mistral Small 4 none | Mistral | 3.4 | 5.2 | 0/4 | 395ms |
| #100 | GPT-5.4 Mini none | OpenAI | 3.1 | 5.1 | 0/4 | 929ms |
| #101 | Qwen3 Coder Next none | Qwen | 3.6 | 5.1 | 0/4 | 3.31s |
| #105 | Qwen3.5-9B none | Qwen | 3.1 | 4.8 | 0/4 | 1.71s |
| #106 | Mercury 2 none | Inception | 3.0 | 4.8 | 0/4 | 483ms |
| #107 | Qwen3 Coder Next medium | Qwen | 3.5 | 4.7 | 0/4 | 8.64s |
| #110 | MiMo-V2-Flash none | Xiaomi | 3.2 | 4.5 | 0/4 | 1.19s |
| #111 | Grok 4.1 Fast none | X AI | 3.2 | 4.5 | 0/4 | 1.07s |
| #112 | Ling 2.6 1t none | Inclusionai | 3.4 | 4.5 | 0/4 | 6.55s |
| #113 | GPT-5.4 Nano none | OpenAI | 3.5 | 4.5 | 0/4 | 1.18s |
| #115 | LFM2-24B-A2B none | Liquid | 3.3 | 4.1 | 0/3 | 471ms |
| #50 | Claude Sonnet 4.6 none | Anthropic | 4.8 | 7.4 | 1/4 | 2.94s |
| #58 | Qwen3.5 Plus 2026-02-15 none | Qwen | 4.8 | 6.8 | 1/4 | 1.91s |
| #62 | DeepSeek V4 Pro none | DeepSeek | 4.8 | 6.7 | 1/4 | 36.1s |
| #64 | GLM 5 none | Z.ai | 4.8 | 6.6 | 1/4 | 2.37s |