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) |
|---|---|---|---|---|---|---|
| #135 | Kimi K2.5 none | Moonshot AI | 6.5 | 5.2 | 1/2 | 2.67s |
| #7 | Gemini 3.5 Flash medium | 9.9 | 9.0 | 2/2 | 2.70s | |
| #43 | MiMo-V2.5-Pro medium | Xiaomi | 9.9 | 7.5 | 2/2 | 2.77s |
| #116 | Hunter Alpha none | OpenRouter | 6.4 | 5.7 | 1/2 | 2.82s |
| #85 | Gemma 4 31B none | 6.5 | 6.5 | 1/2 | 2.84s | |
| #158 | GLM 4.7 Flash medium | Z.ai | 6.2 | 4.4 | 1/2 | 2.97s |
| #15 | GPT-5.3-Codex medium | OpenAI | 10.0 | 8.4 | 2/2 | 3.04s |
| #21 | GPT-5.4 medium | OpenAI | 10.0 | 8.0 | 2/2 | 3.11s |
| #42 | GPT-5.2 medium | OpenAI | 9.9 | 7.5 | 2/2 | 3.12s |
| #35 | Gemini 3 PRO Preview medium | 9.8 | 7.6 | 2/2 | 3.26s | |
| #10 | Claude Opus 4.8 medium | Anthropic | 10.0 | 8.7 | 2/2 | 3.32s |
| #2 | Gemini 3.5 Flash high | 10.0 | 9.6 | 2/2 | 3.35s | |
| #51 | Mimo V2 PRO medium | Xiaomi | 9.9 | 7.4 | 2/2 | 3.36s |
| #9 | GPT-5.5 medium | OpenAI | 10.0 | 8.8 | 2/2 | 3.36s |
| #20 | Gemini 3.5 Flash none | 9.8 | 8.1 | 2/2 | 3.38s |