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) |
|---|---|---|---|---|---|---|
| #76 | Kimi K2.5 medium | Moonshot AI | 10.0 | 6.8 | 2/2 | 92.5s |
| #12 | Gemini 3.1 Flash Lite Preview high | 9.8 | 8.6 | 2/2 | 64.0s | |
| #49 | Qwen3.5-Flash medium | Qwen | 10.0 | 7.4 | 2/2 | 63.5s |
| #103 | DeepSeek V4 Pro high | DeepSeek | 10.0 | 6.0 | 2/2 | 41.2s |
| #78 | Qwen3.6 27B medium | Qwen | 10.0 | 6.8 | 2/2 | 38.0s |
| #72 | DeepSeek V3.2 medium | DeepSeek | 10.0 | 7.0 | 2/2 | 35.8s |
| #82 | Hy3 preview high | Tencent | 10.0 | 6.6 | 2/2 | 34.4s |
| #25 | Qwen3.5 Plus 2026-02-15 medium | Qwen | 10.0 | 7.9 | 2/2 | 31.9s |
| #96 | Ring-2.6-1T none | Inclusionai | 9.8 | 6.2 | 2/2 | 27.4s |
| #66 | Qwen3.5-35B-A3B medium | Qwen | 10.0 | 7.1 | 2/2 | 24.4s |
| #14 | Qwen3.6 Max Preview medium | Qwen | 10.0 | 8.5 | 2/2 | 24.3s |
| #53 | Gemini 3.1 Flash Lite high | 7.3 | 7.3 | 1/2 | 23.3s | |
| #36 | Qwen3.5 Plus 2026-04-20 medium | Qwen | 10.0 | 7.6 | 2/2 | 20.2s |
| #30 | Qwen3.5-27B medium | Qwen | 10.0 | 7.8 | 2/2 | 19.7s |
| #38 | Grok 4.3 medium | X AI | 9.8 | 7.6 | 2/2 | 18.6s |