Kategori AI BENCHY
Peringkat Spesifik domain
Lihat model AI mana yang paling baik di Spesifik domain, mana yang tetap andal, dan di mana kesenjangan terbesar muncul. Urutkan berdasarkan: Tes benar ↑.
| Peringkat | Model | Perusahaan | Skor Spesifik domain | Skor | Tes benar | Waktu respons (rata-rata) |
|---|---|---|---|---|---|---|
| #148 | GPT-5.4 Nano none | OpenAI | 2.9 | 4.7 | 0/3 | 926ms |
| #149 | Nemotron 3 Nano Omni 30b A3b Reasoning medium | NVIDIA | 2.9 | 4.6 | 0/3 | 56.7s |
| #153 | Qwen3.6 35B A3B none | Qwen | 3.5 | 4.6 | 0/3 | 7.45s |
| #154 | Qwen3.5-9B none | Qwen | 3.0 | 4.6 | 0/3 | 464ms |
| #156 | Hy3 preview none | Tencent | 3.6 | 4.4 | 0/3 | 17.6s |
| #158 | GLM 4.7 Flash medium | Z.ai | 3.5 | 4.4 | 0/3 | 174.6s |
| #159 | Ling-2.6-1T none | Inclusionai | 3.0 | 4.3 | 0/3 | 1.04s |
| #161 | Qwen3.5-9B medium | Qwen | 3.6 | 4.2 | 0/3 | 137.7s |
| #162 | Nemotron 3 Nano Omni 30b A3b Reasoning none | NVIDIA | 3.6 | 4.1 | 0/3 | 489ms |
| #163 | Granite 4.1 8B none | IBM Granite | 3.0 | 4.0 | 0/3 | 357ms |
| #5 | Qwen3.7 Max medium | Qwen | 5.9 | 9.1 | 1/3 | 24.9s |
| #6 | GPT-5.5 low | OpenAI | 5.3 | 9.0 | 1/3 | 28.1s |
| #9 | GPT-5.5 medium | OpenAI | 5.3 | 8.8 | 1/3 | 164.1s |
| #10 | Claude Opus 4.8 medium | Anthropic | 5.3 | 8.7 | 1/3 | 14.2s |
| #12 | Gemini 3.1 Flash Lite Preview high | 5.3 | 8.6 | 1/3 | 127.6s |