Kegagalan kategori AI BENCHY
Kecerdasan umum: Tidak mengikuti instruksi
Kecerdasan umum
Tidak mengikuti instruksi
Lihat model AI mana yang paling mungkin mengalami Tidak mengikuti instruksi di Kecerdasan umum, 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 | 6.1 | 0/1 | 101.4s |
| #46 | Kimi K2.5 medium | Moonshot AI | 1 | 6.5 | 0/1 | 69.7s |
| #32 | Qwen3.5-Flash medium | Qwen | 1 | 6.1 | 0/1 | 40.1s |
| #80 | MiniMax M2.7 medium | Minimax | 1 | 3.9 | 0/1 | 38.7s |
| #39 | Seed-2.0-Mini medium | Bytedance Seed | 1 | 5.1 | 0/1 | 36.7s |
| #27 | DeepSeek V3.2 medium | DeepSeek | 1 | 5.4 | 0/1 | 31.3s |
| #51 | Nemotron 3 Super medium | NVIDIA | 1 | 3.8 | 0/1 | 27.9s |
| #9 | Qwen3.6 Plus Preview medium | Qwen | 1 | 5.1 | 0/1 | 27.1s |
| #20 | Qwen3.6 Plus medium | Qwen | 1 | 5.1 | 0/1 | 27.1s |
| #88 | Nemotron 3 Super none | NVIDIA | 1 | 4.2 | 0/1 | 25.0s |
| #6 | Seed-2.0-Lite medium | Bytedance Seed | 1 | 6.7 | 0/1 | 18.2s |
| #57 | GPT-5 Nano medium | OpenAI | 1 | 4.1 | 0/1 | 17.5s |
| #52 | Grok 4.1 Fast medium | X AI | 1 | 4.2 | 0/1 | 16.2s |
| #13 | GLM 5 medium | Z.ai | 1 | 6.1 | 0/1 | 14.7s |
| #45 | GPT-5 Mini medium | OpenAI | 1 | 4.5 | 0/1 | 13.5s |