Kegagalan kategori AI BENCHY
Pemrograman: Jawaban salah
Pemrograman
Jawaban salah
Lihat model AI mana yang paling mungkin mengalami Jawaban salah di Pemrograman, agar Anda bisa menemukan titik lemahnya lebih cepat. Urutkan berdasarkan: Waktu respons (rata-rata) ↑.
Alasan kegagalan
| Peringkat | Model | Perusahaan | Jumlah Jawaban salah | Skor kategori | Tes benar | Waktu respons (rata-rata) |
|---|---|---|---|---|---|---|
| #85 | Mercury 2 none | Inception | 1 | 3.6 | 0/1 | 969ms |
| #75 | Grok 4.20 Beta none | X AI | 1 | 5.5 | 0/1 | 1.14s |
| #77 | Grok 4.20 none | X AI | 1 | 3.4 | 0/1 | 1.22s |
| #78 | Mistral Small 4 none | Mistral | 1 | 4.5 | 0/1 | 1.28s |
| #90 | GPT-5.4 Nano none | OpenAI | 1 | 7.1 | 0/1 | 1.43s |
| #52 | MiMo-V2-Omni none | Xiaomi | 1 | 6.6 | 0/1 | 1.72s |
| #89 | Grok 4.1 Fast none | X AI | 1 | 5.3 | 0/1 | 1.79s |
| #83 | GPT-4o-mini none | OpenAI | 1 | 3.0 | 0/1 | 2.55s |
| #88 | MiMo-V2-Flash none | Xiaomi | 1 | 6.3 | 0/1 | 2.79s |
| #82 | Nemotron 3 Super none | NVIDIA | 1 | 3.3 | 0/1 | 2.99s |
| #81 | Qwen3 Coder Next none | Qwen | 1 | 7.3 | 0/1 | 3.14s |
| #66 | Qwen3.5-122B-A10B none | Qwen | 1 | 4.3 | 0/1 | 3.44s |
| #46 | Qwen3.5 Plus 2026-02-15 none | Qwen | 1 | 6.3 | 0/1 | 3.63s |
| #73 | GLM 5 Turbo none | Z.ai | 1 | 5.3 | 0/1 | 3.93s |
| #70 | GLM 4.7 Flash none | Z.ai | 1 | 6.4 | 0/1 | 5.57s |