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: Tes benar ↓.
461/461
Filter model
Tidak ada model yang cocok dengan pencarian dan filter saat ini.
| Peringkat | Model | Perusahaan | Skor Kepatuhan instruksi | Skor | Total Biaya | Tes benar | Waktu respons (rata-rata) |
|---|---|---|---|---|---|---|---|
| #455 | LFM2-24B-A2B default | Liquid | 0.6 | 0.2 | $0.001 | 1/2 | 752ms |
| #203 | Minimax M3.1 Flash max | Minimax | 0.5 | 0.7 | $0.000 | 0/2 | 1.73s |
| #215 | Space Bunny Alpha max | Stealth | 0.6 | 0.7 | $0.000 | 0/2 | 3.78s |
| #230 | Qwen3.7 Flash medium | Qwen | 0.6 | 0.7 | $0.076 | 0/2 | 9.27s |
| #237 | Minimax M3.1 Flash high | Minimax | 0.5 | 0.7 | $0.000 | 0/2 | 1.65s |
| #252 | Minimax M3.1 Flash xhigh | Minimax | 0.5 | 0.6 | $0.000 | 0/2 | 1.72s |
| #265 | Minimax M3.1 Flash medium | Minimax | 0.5 | 0.6 | $0.000 | 0/2 | 1.72s |
| #273 | Trinity Large Thinking low | Arcee AI | 0.4 | 0.6 | $0.918 | 0/2 | 4.07s |
| #276 | Space Bunny Alpha xhigh | Stealth | 0.6 | 0.6 | $0.000 | 0/2 | 2.22s |
| #279 | DeepSeek V4 Flash 0731 none | DeepSeek | 0.5 | 0.6 | $0.053 | 0/2 | 1.42s |
| #284 | Trinity Large Thinking medium | Arcee AI | 0.4 | 0.6 | $0.862 | 0/2 | 3.99s |
| #289 | Granite 4.2 8B medium | IBM Granite | 0.4 | 0.6 | $0.029 | 0/2 | 36.9s |
| #317 | Space Bunny Alpha low | Stealth | 0.4 | 0.6 | $0.000 | 0/2 | 1.43s |
| #341 | Granite 4.2 8B low | IBM Granite | 0.3 | 0.5 | $0.036 | 0/2 | 75.8s |
| #344 | Laguna XS 2.1 none | Poolside | 0.4 | 0.5 | $0.020 | 0/2 | 364ms |