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: Tes benar ↓.
Model yang ditampilkan
15
Rata-rata Skor Kepatuhan instruksi
8.5
Model terbaik
Gemini 3 Flash Preview 10.0| Peringkat | Model | Perusahaan | Skor Kepatuhan instruksi | Skor | Tes benar | Waktu respons (rata-rata) |
|---|---|---|---|---|---|---|
| #107 | Laguna Xs.2 medium | Poolside | 10.0 | 5.8 | 2/2 | 1.68s |
| #110 | Seed-2.0-Lite none | Bytedance Seed | 10.0 | 5.8 | 2/2 | 1.06s |
| #112 | GLM 5.1 none | Z.ai | 9.8 | 5.7 | 2/2 | 1.98s |
| #119 | Cobuddy medium | Baidu | 9.8 | 5.6 | 2/2 | 11.6s |
| #126 | gpt-oss-120b none | OpenAI | 9.8 | 5.4 | 2/2 | 5.06s |
| #133 | DeepSeek V3.2 none | DeepSeek | 10.0 | 5.2 | 2/2 | 1.52s |
| #136 | Elephant Alpha medium | Openrouter | 9.8 | 5.1 | 2/2 | 987ms |
| #137 | Elephant Alpha none | Openrouter | 9.8 | 5.1 | 2/2 | 1.03s |
| #138 | Ling-2.6-flash none | Inclusionai | 9.8 | 5.0 | 2/2 | 5.52s |
| #32 | Gemini 3.5 Flash minimal | 6.4 | 7.7 | 1/2 | 893ms | |
| #48 | Gemini 3 Flash Preview none | 6.4 | 7.4 | 1/2 | 1.58s | |
| #53 | Gemini 3.1 Flash Lite high | 7.3 | 7.3 | 1/2 | 23.3s | |
| #55 | GLM 5.1 medium | Z.ai | 6.4 | 7.3 | 1/2 | 7.47s |
| #62 | Step 3.5 Flash medium | Stepfun | 8.3 | 7.2 | 1/2 | 4.78s |
| #77 | Claude Sonnet 4.6 none | Anthropic | 6.5 | 6.8 | 1/2 | 1.96s |