Kategori AI BENCHY
Peringkat Kecerdasan umum
Lihat model AI mana yang paling baik di Kecerdasan umum, mana yang tetap andal, dan di mana kesenjangan terbesar muncul. Urutkan berdasarkan: Metrik ↑.
| Peringkat | Model | Perusahaan | Skor Kecerdasan umum | Skor | Tes benar | Waktu respons (rata-rata) |
|---|---|---|---|---|---|---|
| #41 | Nemotron 3 Ultra 550b A55b medium | NVIDIA | 3.7 | 7.5 | 0/1 | 2.52s |
| #42 | GPT-5.2 medium | OpenAI | 3.7 | 7.5 | 0/1 | 4.32s |
| #129 | MiniMax M2.5 medium | Minimax | 3.8 | 5.3 | 0/1 | 6.63s |
| #148 | GPT-5.4 Nano none | OpenAI | 3.8 | 4.7 | 0/1 | 1.31s |
| #130 | MiniMax M2.7 medium | Minimax | 3.9 | 5.3 | 0/1 | 38.7s |
| #65 | Grok 4.20 medium | X AI | 3.9 | 7.1 | 0/1 | 24.5s |
| #22 | Step 3.7 Flash medium | Stepfun | 4.0 | 8.0 | 0/1 | 6.85s |
| #50 | Gemini 3.1 Flash Lite Preview low | 4.0 | 7.4 | 0/1 | 1.54s | |
| #58 | Gemini 3.1 Flash Lite Preview none | 4.0 | 7.2 | 0/1 | 741ms | |
| #61 | Gemini 3.1 Flash Lite low | 4.0 | 7.2 | 0/1 | 1.37s | |
| #64 | MiMo-V2-Flash medium | Xiaomi | 4.0 | 7.2 | 0/1 | 4.20s |
| #83 | Step 3.5 Flash none | Stepfun | 4.0 | 6.6 | 0/1 | 14.4s |
| #87 | Gemini 3.1 Flash Lite minimal | 4.0 | 6.4 | 0/1 | 791ms | |
| #90 | Gemini 3.1 Flash Lite none | 4.0 | 6.4 | 0/1 | 992ms | |
| #102 | Gemma 4 26B A4B none | 4.0 | 6.0 | 0/1 | 3.54s |