Ranking de Truques anti-IA
Veja quais modelos de IA vão melhor em Truques anti-IA, quais permanecem confiáveis e onde aparecem as maiores diferenças. Ordenar por: Custo total ↑.
210/210
Filtrar modelos
Nenhum modelo corresponde à pesquisa e aos filtros atuais.
| Posição | Modelo | Empresa | Pontuação de Truques anti-IA | Pontuação | Custo total | Testes corretos | Tempo de resposta (médio) |
|---|---|---|---|---|---|---|---|
| #100 | Hy3 preview medium | Tencent | 10.0 | 6.5 | $0.018 | 4/4 | 6.59s |
| #121 | gpt-oss-120b medium | OpenAI | 6.7 | 6.1 | $0.019 | 2/4 | 10.2s |
| #209 | Step 3.5 Flash none | Stepfun | 10.0 | 2.3 | $0.020 | 4/4 | 35.0s |
| #169 | Qwen3.5-9B none | Qwen | 3.1 | 5.1 | $0.021 | 0/4 | 1.71s |
| #157 | Mimo V2 Omni none | Xiaomi | 3.6 | 5.5 | $0.021 | 0/4 | 1.63s |
| #165 | Mistral Small 4 none | Mistral | 3.4 | 5.1 | $0.022 | 0/4 | 395ms |
| #166 | Qwen3 Coder Next none | Qwen | 3.6 | 5.1 | $0.025 | 0/4 | 3.31s |
| #200 | MiMo-V2-Flash none | Xiaomi | 3.2 | 4.0 | $0.025 | 0/4 | 1.19s |
| #168 | MiMo-V2.5 none | Xiaomi | 3.5 | 5.1 | $0.025 | 0/4 | 2.19s |
| #179 | Ring-2.6-1T none | Inclusionai | 9.2 | 4.8 | $0.026 | 3/4 | 43.3s |
| #189 | Mercury 2 none | Inception | 3.0 | 4.6 | $0.030 | 0/4 | 483ms |
| #187 | Qwen3 Coder Next medium | Qwen | 3.5 | 4.7 | $0.032 | 0/4 | 8.64s |
| #186 | Laguna M.1 medium | Poolside | 6.5 | 4.7 | $0.033 | 2/4 | 4.87s |
| #115 | Gemma 4 31B none | 6.5 | 6.2 | $0.035 | 2/4 | 1.85s | |
| #204 | Qwen3.5-9B medium | Qwen | 5.1 | 3.8 | $0.036 | 1/4 | 34.4s |