Kegagalan AI BENCHY
Kegagalan Format tambahan
Lihat model AI mana yang paling sering mengalami Format tambahan, agar Anda bisa melihat risiko keandalan sebelum memilih.
Kategori terkait
| Peringkat | Model | Perusahaan | Jumlah Format tambahan | Skor Rata-rata | Tes benar | Waktu respons (rata-rata) |
|---|---|---|---|---|---|---|
| #26 | Claude Opus 4.6 medium | Anthropic | 4 | 6.6 | 10/16 | 22.9s |
| #25 | Claude Sonnet 4.6 none | Anthropic | 3 | 6.8 | 10/16 | 5.57s |
| #11 | Claude Sonnet 4.6 medium | Anthropic | 2 | 7.7 | 12/16 | 11.2s |
| #33 | DeepSeek V3.2 none | DeepSeek | 2 | 5.5 | 7/16 | 12.9s |
| #48 | Qwen3 Coder Next none | Qwen | 1 | 4.0 | 4/16 | 11.7s |
| #54 | MiMo-V2-Flash none | Xiaomi | 1 | 2.9 | 3/16 | 2.97s |