Kegagalan kategori AI BENCHY
Pemecahan teka-teki: Tidak mengikuti instruksi
Pemecahan teka-teki
Tidak mengikuti instruksi
Lihat model AI mana yang paling mungkin mengalami Tidak mengikuti instruksi di Pemecahan teka-teki, agar Anda bisa menemukan titik lemahnya lebih cepat. Urutkan berdasarkan: Waktu respons (rata-rata) ↓.
Alasan kegagalan
| Peringkat | Model | Perusahaan | Jumlah Tidak mengikuti instruksi | Skor kategori | Tes benar | Waktu respons (rata-rata) |
|---|---|---|---|---|---|---|
| #10 | Qwen3.5-27B medium | Qwen | 1 | 8.2 | 2/3 | 64.6s |
| #46 | Kimi K2.5 medium | Moonshot AI | 1 | 5.3 | 1/3 | 45.4s |
| #97 | Qwen3.5-9B medium | Qwen | 1 | 3.1 | 0/3 | 33.4s |
| #14 | Gemma 4 31B medium | 1 | 8.8 | 2/3 | 27.6s | |
| #80 | MiniMax M2.7 medium | Minimax | 2 | 3.8 | 0/3 | 25.6s |
| #34 | Kimi K2.6 medium | Moonshot AI | 2 | 5.0 | 0/3 | 25.6s |
| #57 | GPT-5 Nano medium | OpenAI | 1 | 5.3 | 1/3 | 19.8s |
| #45 | GPT-5 Mini medium | OpenAI | 1 | 5.6 | 1/3 | 14.1s |
| #93 | GLM 4.7 Flash medium | Z.ai | 1 | 2.9 | 0/3 | 12.9s |
| #68 | gpt-oss-120b medium | OpenAI | 2 | 3.2 | 0/3 | 11.8s |
| #6 | Seed-2.0-Lite medium | Bytedance Seed | 1 | 9.0 | 2/3 | 11.0s |
| #31 | GLM 5V Turbo medium | Z.ai | 1 | 7.7 | 2/3 | 10.9s |
| #16 | GPT-5.4 medium | OpenAI | 1 | 8.2 | 2/3 | 9.13s |
| #24 | Gemma 4 26B A4B medium | 1 | 7.9 | 2/3 | 8.52s | |
| #51 | Nemotron 3 Super medium | NVIDIA | 2 | 3.5 | 0/3 | 8.39s |