Kategori AI BENCHY
Peringkat Kepatuhan instruksi
Lihat model AI mana yang paling baik di Kepatuhan instruksi, mana yang tetap andal, dan di mana kesenjangan terbesar muncul. Urutkan berdasarkan: Waktu respons (rata-rata) ↑.
| Peringkat | Model | Perusahaan | Skor Kepatuhan instruksi | Skor | Tes benar | Waktu respons (rata-rata) |
|---|---|---|---|---|---|---|
| #163 | Granite 4.1 8B none | IBM Granite | 3.6 | 4.0 | 0/2 | 344ms |
| #142 | Mistral Small 4 none | Mistral | 6.5 | 4.9 | 1/2 | 380ms |
| #146 | Laguna Xs.2 none | Poolside | 6.5 | 4.8 | 1/2 | 439ms |
| #127 | Grok 4.20 none | X AI | 6.3 | 5.4 | 1/2 | 445ms |
| #131 | Qwen3.5-122B-A10B none | Qwen | 6.3 | 5.3 | 1/2 | 513ms |
| #154 | Qwen3.5-9B none | Qwen | 6.5 | 4.6 | 1/2 | 514ms |
| #162 | Nemotron 3 Nano Omni 30b A3b Reasoning none | NVIDIA | 4.8 | 4.1 | 0/2 | 541ms |
| #155 | Mercury 2 none | Inception | 6.5 | 4.5 | 1/2 | 551ms |
| #97 | Gemini 2.5 Flash none | 10.0 | 6.2 | 2/2 | 590ms | |
| #129 | MiniMax M2.5 medium | Minimax | 7.5 | 5.3 | 1/2 | 621ms |
| #106 | Grok 4.20 Beta none | X AI | 6.3 | 5.8 | 1/2 | 649ms |
| #145 | Laguna M.1 none | Poolside | 6.3 | 4.8 | 1/2 | 683ms |
| #157 | Grok 4.1 Fast none | X AI | 3.0 | 4.4 | 0/2 | 685ms |
| #102 | Gemma 4 26B A4B none | 6.3 | 6.0 | 1/2 | 690ms | |
| #144 | GPT-5.4 Mini none | OpenAI | 6.3 | 4.9 | 1/2 | 728ms |