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: Tes benar ↑.
| Peringkat | Model | Perusahaan | Skor Kecerdasan umum | Skor | Tes benar | Waktu respons (rata-rata) |
|---|---|---|---|---|---|---|
| #6 | Seed-2.0-Lite medium | Bytedance Seed | 6.7 | 8.6 | 0/1 | 18.2s |
| #7 | GPT-5.3-Codex medium | OpenAI | 4.6 | 8.6 | 0/1 | 4.87s |
| #8 | Qwen3.5 Plus 2026-02-15 medium | Qwen | 4.7 | 8.5 | 0/1 | 79.9s |
| #9 | Qwen3.6 Plus Preview medium | Qwen | 5.1 | 8.5 | 0/1 | 27.1s |
| #10 | Qwen3.5-27B medium | Qwen | 6.1 | 8.4 | 0/1 | 101.4s |
| #13 | GLM 5 medium | Z.ai | 6.1 | 8.4 | 0/1 | 14.7s |
| #15 | Gemini 2.5 Flash medium | 4.8 | 8.2 | 0/1 | 4.86s | |
| #16 | GPT-5.4 medium | OpenAI | 4.7 | 8.2 | 0/1 | 4.92s |
| #18 | GLM 5 Turbo medium | Z.ai | 6.1 | 8.1 | 0/1 | 10.1s |
| #19 | Qwen3.5-122B-A10B medium | Qwen | 3.4 | 8.1 | 0/1 | 34.1s |
| #20 | Qwen3.6 Plus medium | Qwen | 5.1 | 8.1 | 0/1 | 27.1s |
| #22 | Gemini 3.1 Flash Lite Preview low | 4.0 | 8.1 | 0/1 | 1.54s | |
| #27 | DeepSeek V3.2 medium | DeepSeek | 5.4 | 8.0 | 0/1 | 31.3s |
| #28 | GPT-5.2 Chat none | OpenAI | 4.4 | 7.9 | 0/1 | 3.20s |
| #29 | Gemini 3.1 Flash Lite Preview none | 4.0 | 7.9 | 0/1 | 741ms |