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: Waktu respons (rata-rata) ↓.
| Peringkat | Model | Perusahaan | Skor Trik anti-AI | Skor | Tes benar | Waktu respons (rata-rata) |
|---|---|---|---|---|---|---|
| #91 | GPT-5.5 none | OpenAI | 6.9 | 6.4 | 2/4 | 1.31s |
| #102 | Gemma 4 26B A4B none | 8.3 | 6.0 | 3/4 | 1.28s | |
| #48 | Gemini 3 Flash Preview none | 8.3 | 7.4 | 3/4 | 1.25s | |
| #125 | GPT-5.4 none | OpenAI | 3.2 | 5.5 | 0/4 | 1.21s |
| #149 | Nemotron 3 Nano Omni 30b A3b Reasoning medium | NVIDIA | 6.4 | 4.6 | 2/4 | 1.20s |
| #152 | MiMo-V2-Flash none | Xiaomi | 3.2 | 4.6 | 0/4 | 1.19s |
| #136 | Elephant Alpha medium | Openrouter | 6.6 | 5.1 | 2/4 | 1.19s |
| #148 | GPT-5.4 Nano none | OpenAI | 3.5 | 4.7 | 0/4 | 1.18s |
| #81 | Mercury 2 medium | Inception | 6.9 | 6.6 | 2/4 | 1.12s |
| #87 | Gemini 3.1 Flash Lite minimal | 8.3 | 6.4 | 3/4 | 1.10s | |
| #34 | Qwen3.7 Max none | Qwen | 6.5 | 7.7 | 2/4 | 1.08s |
| #157 | Grok 4.1 Fast none | X AI | 3.2 | 4.4 | 0/4 | 1.07s |
| #90 | Gemini 3.1 Flash Lite none | 7.5 | 6.4 | 2/4 | 1.07s | |
| #58 | Gemini 3.1 Flash Lite Preview none | 7.5 | 7.2 | 2/4 | 1.04s | |
| #137 | Elephant Alpha none | Openrouter | 6.6 | 5.1 | 2/4 | 963ms |