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 ↓.
Model yang ditampilkan
15
Rata-rata Skor Kepatuhan instruksi
8.5
Model terbaik
Gemini 3.6 Flash 10.0
316/316
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) |
|---|---|---|---|---|---|---|---|
| #226 | GLM 5V Turbo none | Z.ai | 6.5 | 5.6 | $0.052 | 1/2 | 1.97s |
| #227 | Owl Alpha medium | Openrouter | 6.5 | 5.6 | $0.000 | 1/2 | 10.2s |
| #228 | Gemma 4 26B A4B none | 6.3 | 5.6 | $0.015 | 1/2 | 690ms | |
| #229 | Mimo V2 PRO none | Xiaomi | 6.5 | 5.6 | $0.045 | 1/2 | 2.51s |
| #230 | Owl Alpha none | Openrouter | 6.4 | 5.6 | $0.000 | 1/2 | 2.63s |
| #232 | Nemotron 3.5 Lightning high | NVIDIA | 8.5 | 5.6 | $0.134 | 1/2 | 4.98s |
| #234 | Qwen3.6 27B none | Qwen | 6.2 | 5.5 | $0.062 | 1/2 | 1.92s |
| #236 | Qwen3.8 27B none | Qwen | 6.3 | 5.5 | ~$0.006 | 1/2 | 582ms |
| #237 | Mimo V2 Omni none | Xiaomi | 6.5 | 5.5 | $0.021 | 1/2 | 4.26s |
| #238 | DeepSeek V4 Flash 0423 none | DeepSeek | 6.5 | 5.4 | $0.039 | 1/2 | 17.5s |
| #241 | GPT-5.6 Luna none | OpenAI | 7.1 | 5.4 | $0.029 | 1/2 | 1.23s |
| #242 | MiMo-V2.5-Pro none | Xiaomi | 6.4 | 5.4 | $0.068 | 1/2 | 1.03s |
| #243 | Kimi K2.5 none | Moonshot AI | 6.5 | 5.4 | $0.101 | 1/2 | 2.67s |
| #246 | Inkling Small none | Thinkingmachines | 6.3 | 5.3 | $0.054 | 1/2 | 767ms |
| #248 | Seed-2.0-Code none | Bytedance Seed | 6.2 | 5.3 | $0.151 | 1/2 | 1.80s |