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) |
|---|---|---|---|---|---|---|
| #52 | Claude Sonnet 4.6 medium | Anthropic | 10.0 | 7.4 | 2/2 | 2.61s |
| #44 | Gemini 3.1 Flash Lite medium | 9.9 | 7.5 | 2/2 | 2.59s | |
| #120 | Mimo V2 PRO none | Xiaomi | 6.5 | 5.6 | 1/2 | 2.51s |
| #69 | Claude Opus 4.6 medium | Anthropic | 10.0 | 7.0 | 2/2 | 2.43s |
| #134 | GLM 5 Turbo none | Z.ai | 6.5 | 5.2 | 1/2 | 2.13s |
| #45 | GPT-5.4 Mini medium | OpenAI | 9.8 | 7.5 | 2/2 | 2.13s |
| #112 | GLM 5.1 none | Z.ai | 9.8 | 5.7 | 2/2 | 1.98s |
| #109 | GLM 5V Turbo none | Z.ai | 6.5 | 5.8 | 1/2 | 1.97s |
| #77 | Claude Sonnet 4.6 none | Anthropic | 6.5 | 6.8 | 1/2 | 1.96s |
| #118 | Qwen3.6 27B none | Qwen | 6.2 | 5.6 | 1/2 | 1.92s |
| #40 | Gemini 3.1 Flash Lite Preview medium | 10.0 | 7.5 | 2/2 | 1.91s | |
| #70 | GPT-5.4 Nano medium | OpenAI | 9.8 | 7.0 | 2/2 | 1.88s |
| #3 | Gemini 3.5 Flash low | 9.9 | 9.4 | 2/2 | 1.86s | |
| #153 | Qwen3.6 35B A3B none | Qwen | 6.2 | 4.6 | 1/2 | 1.86s |
| #22 | Step 3.7 Flash medium | Stepfun | 9.8 | 8.0 | 2/2 | 1.83s |