Trik anti-AI: Jawaban salah
Trik anti-AI
Jawaban salah
Lihat model AI mana yang paling mungkin mengalami Jawaban salah di Trik anti-AI, agar Anda bisa menemukan titik lemahnya lebih cepat. Urutkan berdasarkan: Waktu respons (rata-rata) ↑.
Alasan kegagalan
140/140
Filter model
Tidak ada model yang cocok dengan pencarian dan filter saat ini.
| Peringkat | Model | Perusahaan | Jumlah Jawaban salah | Skor kategori | Total Biaya | Tes benar | Waktu respons (rata-rata) |
|---|---|---|---|---|---|---|---|
| #165 | Mistral Small 4 none | Mistral | 4 | 3.4 | $0.022 | 0/4 | 395ms |
| #210 | LFM2-24B-A2B none | Liquid | 3 | 2.5 | $0.001 | 0/3 | 471ms |
| #189 | Mercury 2 none | Inception | 4 | 3.0 | $0.030 | 0/4 | 483ms |
| #197 | Grok 4.20 none | X AI | 3 | 4.8 | $0.057 | 1/4 | 501ms |
| #205 | Laguna Xs.2 none | Poolside | 2 | 3.0 | $0.004 | 0/4 | 534ms |
| #118 | Gemini 2.5 Flash none | 4 | 3.0 | $0.017 | 0/4 | 582ms | |
| #208 | Nemotron 3 Nano Omni 30b A3b Reasoning none | NVIDIA | 2 | 4.8 | $0.000 | 1/4 | 584ms |
| #191 | Grok 4.20 Beta none | X AI | 4 | 4.0 | $0.087 | 0/4 | 597ms |
| #192 | Laguna M.1 none | Poolside | 3 | 3.4 | $0.009 | 0/4 | 705ms |
| #160 | Laguna XS 2.1 none | Poolside | 2 | 5.3 | $0.008 | 1/4 | 755ms |
| #103 | Qwen3.5-27B none | Qwen | 3 | 4.8 | $0.090 | 1/4 | 788ms |
| #201 | Granite 4.1 8B none | IBM Granite | 2 | 4.9 | $0.007 | 1/4 | 844ms |
| #88 | Gemini 3.5 Flash minimal | 2 | 6.5 | $0.300 | 2/4 | 892ms | |
| #159 | GPT-5.6 Luna none | OpenAI | 3 | 4.8 | $0.142 | 1/4 | 901ms |
| #136 | GPT-5.4 Mini none | OpenAI | 4 | 3.1 | $0.095 | 0/4 | 929ms |