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) |
|---|---|---|---|---|---|---|
| #85 | Elephant none | Openrouter | 9.8 | 5.2 | 2/2 | 1.03s |
| #61 | Seed-2.0-Lite none | Bytedance Seed | 10.0 | 6.2 | 2/2 | 1.06s |
| #54 | Mercury 2 medium | Inception | 10.0 | 6.5 | 2/2 | 1.07s |
| #66 | GPT-5.4 none | OpenAI | 6.5 | 5.9 | 1/2 | 1.07s |
| #60 | Gemma 4 26B A4B none | 4.4 | 6.2 | 0/2 | 1.08s | |
| #98 | LFM2-24B-A2B none | Liquid | 4.8 | 4.1 | 0/2 | 1.09s |
| #78 | Trinity Large Preview none | Arcee AI | 4.1 | 5.3 | 0/2 | 1.09s |
| #29 | Gemini 3.1 Flash Lite Preview none | 10.0 | 7.9 | 2/2 | 1.13s | |
| #89 | GPT-4o-mini none | OpenAI | 4.8 | 4.9 | 0/2 | 1.27s |
| #73 | Mistral Small 4 medium | Mistral | 7.3 | 5.7 | 1/2 | 1.38s |
| #4 | Claude Opus 4.7 none | Anthropic | 10.0 | 9.2 | 2/2 | 1.46s |
| #53 | GLM 5 none | Z.ai | 10.0 | 6.6 | 2/2 | 1.48s |
| #22 | Gemini 3.1 Flash Lite Preview low | 10.0 | 8.1 | 2/2 | 1.49s | |
| #88 | Nemotron 3 Super none | NVIDIA | 4.9 | 5.1 | 0/2 | 1.50s |
| #64 | DeepSeek V3.2 none | DeepSeek | 10.0 | 6.1 | 2/2 | 1.52s |