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) |
|---|---|---|---|---|---|---|
| #10 | Qwen3.5-27B medium | Qwen | 8.2 | 8.4 | 2/3 | 64.6s |
| #32 | Qwen3.5-Flash medium | Qwen | 6.4 | 7.8 | 1/3 | 56.7s |
| #11 | Gemini 3.1 Flash Lite Preview high | 7.7 | 8.4 | 2/3 | 46.3s | |
| #46 | Kimi K2.5 medium | Moonshot AI | 5.3 | 7.0 | 1/3 | 45.4s |
| #27 | DeepSeek V3.2 medium | DeepSeek | 8.2 | 8.0 | 2/3 | 36.9s |
| #8 | Qwen3.5 Plus 2026-02-15 medium | Qwen | 10.0 | 8.5 | 3/3 | 34.6s |
| #97 | Qwen3.5-9B medium | Qwen | 3.1 | 4.4 | 0/3 | 33.4s |
| #43 | Qwen3.5-35B-A3B medium | Qwen | 6.4 | 7.4 | 1/3 | 31.6s |
| #14 | Gemma 4 31B medium | 8.8 | 8.3 | 2/3 | 27.6s | |
| #39 | Seed-2.0-Mini medium | Bytedance Seed | 8.2 | 7.5 | 2/3 | 25.9s |
| #80 | MiniMax M2.7 medium | Minimax | 3.8 | 5.3 | 0/3 | 25.6s |
| #34 | Kimi K2.6 medium | Moonshot AI | 5.0 | 7.7 | 0/3 | 25.6s |
| #33 | GLM 5.1 medium | Z.ai | 8.2 | 7.8 | 2/3 | 23.8s |
| #87 | Qwen3 Coder Next none | Qwen | 3.2 | 5.1 | 0/3 | 22.9s |
| #57 | GPT-5 Nano medium | OpenAI | 5.3 | 6.3 | 1/3 | 19.8s |