Kategori AI BENCHY
Peringkat Trik anti-AI
Lihat model AI mana yang paling baik di Trik anti-AI, mana yang tetap andal, dan di mana kesenjangan terbesar muncul. Urutkan berdasarkan: Total Biaya ↓.
Model yang ditampilkan
15
Rata-rata Skor Trik anti-AI
6.9
Model terbaik
Grok 4.20 Multi Agent Beta 6.9
169/169
Filter model
Tidak ada model yang cocok dengan pencarian dan filter saat ini.
| Peringkat | Model | Perusahaan | Skor Trik anti-AI | Skor | Total Biaya | Tes benar | Waktu respons (rata-rata) |
|---|---|---|---|---|---|---|---|
| #26 | Nemotron 3 Ultra 550b A55b medium | NVIDIA | 10.0 | 8.1 | $0.158 | 4/4 | 8.62s |
| #41 | DeepSeek V4 Pro high | DeepSeek | 5.7 | 7.6 | $0.157 | 1/4 | 25.7s |
| #75 | Qwen3.6 35B A3B medium | Qwen | 10.0 | 6.7 | $0.146 | 4/4 | 6.02s |
| #40 | MiniMax M3 medium | Minimax | 5.5 | 7.6 | $0.131 | 1/4 | 14.9s |
| #112 | GPT-5.4 none | OpenAI | 3.2 | 5.8 | $0.122 | 0/4 | 1.21s |
| #52 | Gemini 3 Flash Preview low | 10.0 | 7.4 | $0.111 | 4/4 | 3.48s | |
| #71 | Gemini 3.5 Flash minimal | 6.5 | 6.8 | $0.108 | 2/4 | 892ms | |
| #46 | GPT-5.4 Nano medium | OpenAI | 8.3 | 7.5 | $0.107 | 3/4 | 4.52s |
| #51 | MiMo-V2.5-Pro medium | Xiaomi | 10.0 | 7.4 | $0.106 | 4/4 | 3.26s |
| #127 | MiniMax M2.7 medium | Minimax | 7.9 | 5.2 | $0.104 | 2/4 | 40.3s |
| #149 | Grok 4.20 Beta none | X AI | 4.0 | 4.7 | $0.087 | 0/4 | 597ms |
| #79 | GPT-5 Nano medium | OpenAI | 6.5 | 6.7 | $0.081 | 2/4 | 25.5s |
| #70 | Qwen3.5-Flash medium | Qwen | 10.0 | 6.8 | $0.080 | 4/4 | 59.1s |
| #111 | Kimi K2.6 none | Moonshot AI | 4.6 | 5.8 | $0.079 | 1/4 | 1.39s |
| #61 | GLM 5.2 none | Z.ai | 8.3 | 7.1 | $0.076 | 3/4 | 3.70s |