Kategori AI BENCHY
Peringkat Gabungan
Lihat model AI mana yang paling baik di Gabungan, mana yang tetap andal, dan di mana kesenjangan terbesar muncul. Urutkan berdasarkan: Metrik ↑.
| Peringkat | Model | Perusahaan | Skor Gabungan | Skor | Tes benar | Waktu respons (rata-rata) |
|---|---|---|---|---|---|---|
| #67 | Qwen3.5-27B none | Qwen | 2.8 | 5.9 | 0/1 | 9.39s |
| #75 | GLM 5.1 none | Z.ai | 2.8 | 5.6 | 0/1 | 32.6s |
| #76 | Kimi K2.5 none | Moonshot AI | 2.8 | 5.5 | 0/1 | 19.2s |
| #93 | GLM 4.7 Flash medium | Z.ai | 2.8 | 4.6 | 0/1 | 65.6s |
| #5 | Gemini 3 Flash Preview low | 3.0 | 8.8 | 0/1 | 3.27s | |
| #12 | Gemini 3 PRO Preview medium | 3.0 | 8.4 | 0/1 | 10.4s | |
| #14 | Gemma 4 31B medium | 3.0 | 8.3 | 0/1 | 0ms | |
| #22 | Gemini 3.1 Flash Lite Preview low | 3.0 | 8.1 | 0/1 | 11.9s | |
| #29 | Gemini 3.1 Flash Lite Preview none | 3.0 | 7.9 | 0/1 | 3.20s | |
| #48 | Gemma 4 31B none | 3.0 | 6.9 | 0/1 | 0ms | |
| #49 | Qwen3.5 Plus 2026-02-15 none | Qwen | 3.0 | 6.8 | 0/1 | 6.65s |
| #53 | GLM 5 none | Z.ai | 3.0 | 6.6 | 0/1 | 4.98s |
| #55 | MiMo-V2-Omni none | Xiaomi | 3.0 | 6.5 | 0/1 | 2.47s |
| #56 | Grok 4.20 Multi Agent Beta medium | X AI | 3.0 | 6.4 | 0/1 | 0ms |
| #58 | GLM 5V Turbo none | Z.ai | 3.0 | 6.2 | 0/1 | 6.51s |