Kegagalan kategori AI BENCHY
Trik anti-AI: Tidak mengikuti instruksi
Trik anti-AI
Tidak mengikuti instruksi
Lihat model AI mana yang paling mungkin mengalami Tidak mengikuti instruksi di Trik anti-AI, agar Anda bisa menemukan titik lemahnya lebih cepat. Urutkan berdasarkan: Waktu respons (rata-rata) ↑.
Alasan kegagalan
| Peringkat | Model | Perusahaan | Jumlah Tidak mengikuti instruksi | Skor kategori | Tes benar | Waktu respons (rata-rata) |
|---|---|---|---|---|---|---|
| #146 | Laguna Xs.2 none | Poolside | 1 | 3.0 | 0/4 | 534ms |
| #163 | Granite 4.1 8B none | IBM Granite | 1 | 4.9 | 1/4 | 844ms |
| #137 | Elephant Alpha none | Openrouter | 1 | 6.6 | 2/4 | 963ms |
| #58 | Gemini 3.1 Flash Lite Preview none | 1 | 7.5 | 2/4 | 1.04s | |
| #157 | Grok 4.1 Fast none | X AI | 1 | 3.2 | 0/4 | 1.07s |
| #81 | Mercury 2 medium | Inception | 1 | 6.9 | 2/4 | 1.12s |
| #101 | Mimo V2 Omni none | Xiaomi | 1 | 3.6 | 0/4 | 1.63s |
| #40 | Gemini 3.1 Flash Lite Preview medium | 1 | 9.1 | 3/4 | 2.33s | |
| #44 | Gemini 3.1 Flash Lite medium | 1 | 9.1 | 3/4 | 2.39s | |
| #123 | MiMo-V2.5-Pro none | Xiaomi | 1 | 3.3 | 0/4 | 2.67s |
| #121 | Owl Alpha none | Openrouter | 1 | 3.4 | 0/4 | 2.78s |
| #140 | Qwen3 Coder Next none | Qwen | 1 | 3.6 | 0/4 | 3.31s |
| #63 | GPT-5.3 Chat none | OpenAI | 1 | 6.7 | 2/4 | 3.86s |
| #42 | GPT-5.2 medium | OpenAI | 1 | 6.5 | 2/4 | 7.81s |
| #150 | Qwen3 Coder Next medium | Qwen | 1 | 3.5 | 0/4 | 8.64s |