Kategori AI BENCHY
Peringkat Pengetahuan umum
Lihat model AI mana yang paling baik di Pengetahuan umum, mana yang tetap andal, dan di mana kesenjangan terbesar muncul. Urutkan berdasarkan: Tes benar ↑.
Alasan kegagalan
| Peringkat | Model | Perusahaan | Skor Pengetahuan umum | Skor | Tes benar | Waktu respons (rata-rata) |
|---|---|---|---|---|---|---|
| #69 | Kimi K2.5 medium | Moonshot AI | 3.0 | 6.8 | 0/1 | 83.9s |
| #70 | Qwen3.6 27B medium | Qwen | 3.0 | 6.8 | 0/1 | 81.0s |
| #72 | GPT-5.5 none | OpenAI | 3.0 | 6.7 | 0/1 | 5.01s |
| #73 | Gemini 3.1 Flash Lite none | 3.0 | 6.7 | 0/1 | 733ms | |
| #75 | Laguna Xs.2 medium | Poolside | 0.0 | 6.6 | 0/0 | 0ms |
| #76 | Qwen3.5 Plus 2026-02-15 none | Qwen | 3.0 | 6.5 | 0/1 | 1.11s |
| #77 | Grok 4.1 Fast medium | X AI | 3.0 | 6.5 | 0/1 | 25.5s |
| #78 | GLM 5 none | Z.ai | 3.0 | 6.5 | 0/1 | 3.62s |
| #79 | MiMo-V2-Omni none | Xiaomi | 3.0 | 6.3 | 0/1 | 1.30s |
| #80 | Mercury 2 medium | Inception | 3.0 | 6.3 | 0/1 | 2.58s |
| #81 | Gemini 2.5 Flash none | 3.0 | 6.3 | 0/1 | 1.15s | |
| #82 | Gemma 4 26B A4B none | 3.0 | 6.3 | 0/1 | 778ms | |
| #83 | GPT-5 Nano medium | OpenAI | 3.0 | 6.2 | 0/1 | 20.1s |
| #84 | DeepSeek V4 Pro none | DeepSeek | 3.0 | 6.2 | 0/1 | 15.6s |
| #85 | Nemotron 3 Super medium | NVIDIA | 3.0 | 6.1 | 0/1 | 55.3s |