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) |
|---|---|---|---|---|---|---|---|
| #156 | Laguna Xs.2 medium | Poolside | 6.9 | 4.3 | $0.000 | 2/4 | 2.68s |
| #164 | gpt-oss-120b none | OpenAI | 6.5 | 4.0 | $0.010 | 2/4 | 32.8s |
| #166 | Nemotron 3 Nano Omni 30b A3b Reasoning medium | NVIDIA | 6.4 | 3.6 | $0.000 | 2/4 | 1.20s |
| #10 | GPT-5.3-Codex medium | OpenAI | 8.7 | 8.9 | $0.740 | 3/4 | 4.16s |
| #13 | Claude Opus 4.7 medium | Anthropic | 8.3 | 8.7 | $0.679 | 3/4 | 1.85s |
| #17 | GPT-5.4 medium | OpenAI | 8.3 | 8.5 | $1.210 | 3/4 | 4.11s |
| #18 | Seed-2.0-Lite medium | Bytedance Seed | 8.3 | 8.5 | $0.175 | 3/4 | 18.0s |
| #19 | GPT-5.2 Chat none | OpenAI | 8.7 | 8.5 | $0.393 | 3/4 | 3.40s |
| #20 | Step 3.7 Flash medium | Stepfun | 8.7 | 8.5 | $0.376 | 3/4 | 9.65s |
| #23 | DeepSeek V4 Flash high | DeepSeek | 8.3 | 8.3 | $0.027 | 3/4 | 28.5s |
| #24 | Gemini 2.5 Flash medium | 8.4 | 8.2 | $0.379 | 3/4 | 6.30s | |
| #27 | GPT-5.4 Mini medium | OpenAI | 8.6 | 8.0 | $0.526 | 3/4 | 4.05s |
| #28 | Qwen3.5 Plus 2026-02-15 medium | Qwen | 8.2 | 8.0 | $0.310 | 3/4 | 45.8s |
| #29 | Qwen3.5-27B medium | Qwen | 8.7 | 7.9 | $0.536 | 3/4 | 19.8s |
| #32 | Gemini 3.1 Flash Lite Preview medium | 9.1 | 7.8 | $0.068 | 3/4 | 2.33s |