Kegagalan AI BENCHY
Kegagalan Tidak mengikuti instruksi
Lihat model AI mana yang paling sering mengalami Tidak mengikuti instruksi, agar Anda bisa melihat risiko keandalan sebelum memilih.
| Peringkat | Model | Perusahaan | Jumlah Tidak mengikuti instruksi | Skor | Tes benar | Waktu respons (rata-rata) |
|---|---|---|---|---|---|---|
| #117 | Grok 4.20 Beta none | X AI | 1 | 5.5 | 5/18 | 1.19s |
| #118 | Nemotron 3 Nano Omni 30b A3b Reasoning medium | NVIDIA | 1 | 5.4 | 10/19 | 17.1s |
| #127 | Laguna Xs.2 none | Poolside | 1 | 5.3 | 9/19 | 806ms |
| #131 | DeepSeek V4 Flash none | DeepSeek | 1 | 5.1 | 5/20 | 27.9s |
| #132 | Qwen3 Coder Next none | Qwen | 1 | 5.1 | 5/20 | 8.83s |
| #135 | Mistral Small 4 none | Mistral | 1 | 5.0 | 5/20 | 658ms |
| #138 | GPT-4o-mini none | OpenAI | 1 | 4.9 | 5/20 | 1.87s |
| #143 | Mercury 2 none | Inception | 1 | 4.6 | 4/20 | 614ms |
| #145 | Nemotron 3 Nano Omni 30b A3b Reasoning none | NVIDIA | 1 | 4.6 | 8/19 | 726ms |
| #151 | Qwen3.5-9B medium | Qwen | 1 | 4.2 | 3/20 | 80.1s |