Kategori AI BENCHY
Peringkat Pemecahan teka-teki
Lihat model AI mana yang paling baik di Pemecahan teka-teki, mana yang tetap andal, dan di mana kesenjangan terbesar muncul. Urutkan berdasarkan: Waktu respons (rata-rata) ↓.
| Peringkat | Model | Perusahaan | Skor Pemecahan teka-teki | Skor | Tes benar | Waktu respons (rata-rata) |
|---|---|---|---|---|---|---|
| #78 | Qwen3.6 27B medium | Qwen | 7.7 | 6.8 | 2/3 | 61.1s |
| #30 | Qwen3.5-27B medium | Qwen | 8.2 | 7.8 | 2/3 | 59.6s |
| #53 | Gemini 3.1 Flash Lite high | 5.7 | 7.3 | 1/3 | 50.8s | |
| #67 | MiniMax M3 medium | Minimax | 7.9 | 7.1 | 2/3 | 49.9s |
| #12 | Gemini 3.1 Flash Lite Preview high | 7.7 | 8.6 | 2/3 | 46.7s | |
| #76 | Kimi K2.5 medium | Moonshot AI | 5.3 | 6.8 | 1/3 | 43.2s |
| #72 | DeepSeek V3.2 medium | DeepSeek | 7.0 | 7.0 | 1/3 | 37.7s |
| #103 | DeepSeek V4 Pro high | DeepSeek | 5.9 | 6.0 | 1/3 | 34.8s |
| #66 | Qwen3.5-35B-A3B medium | Qwen | 8.2 | 7.1 | 2/3 | 33.1s |
| #25 | Qwen3.5 Plus 2026-02-15 medium | Qwen | 10.0 | 7.9 | 3/3 | 32.5s |
| #161 | Qwen3.5-9B medium | Qwen | 3.0 | 4.2 | 0/3 | 32.3s |
| #73 | Seed-2.0-Mini medium | Bytedance Seed | 8.2 | 6.9 | 2/3 | 31.8s |
| #55 | GLM 5.1 medium | Z.ai | 8.2 | 7.3 | 2/3 | 31.6s |
| #96 | Ring-2.6-1T none | Inclusionai | 7.7 | 6.2 | 2/3 | 31.5s |
| #82 | Hy3 preview high | Tencent | 7.7 | 6.6 | 2/3 | 27.9s |