Kegagalan kategori AI BENCHY
Pemrograman: Kedaluwarsa
Pemrograman
Kedaluwarsa
Lihat model AI mana yang paling mungkin mengalami Kedaluwarsa di Pemrograman, agar Anda bisa menemukan titik lemahnya lebih cepat. Urutkan berdasarkan: Waktu respons (rata-rata) ↑.
Alasan kegagalan
| Peringkat | Model | Perusahaan | Jumlah Kedaluwarsa | Skor kategori | Tes benar | Waktu respons (rata-rata) |
|---|---|---|---|---|---|---|
| #67 | MiniMax M2.5 medium | Minimax | 1 | 3.0 | 0/1 | 0ms |
| #86 | Qwen3 Coder Next medium | Qwen | 1 | 4.7 | 0/1 | 1.69s |
| #57 | Gemma 4 26B A4B none | 1 | 4.7 | 0/1 | 7.07s | |
| #38 | MiMo-V2-Flash medium | Xiaomi | 1 | 4.7 | 0/1 | 13.0s |
| #87 | GLM 4.7 Flash medium | Z.ai | 1 | 3.6 | 0/1 | 21.3s |
| #30 | Qwen3.5-Flash medium | Qwen | 1 | 4.7 | 0/1 | 45.7s |
| #12 | Gemma 4 31B medium | 1 | 4.7 | 0/1 | 71.0s | |
| #17 | Qwen3.5-122B-A10B medium | Qwen | 1 | 4.7 | 0/1 | 71.0s |
| #31 | GLM 5.1 medium | Z.ai | 1 | 4.7 | 0/1 | 118.5s |
| #22 | Gemma 4 26B A4B medium | 1 | 2.8 | 0/1 | 147.5s | |
| #43 | Kimi K2.5 medium | Moonshot AI | 1 | 4.7 | 0/1 | 150.8s |
| #25 | DeepSeek V3.2 medium | DeepSeek | 1 | 4.7 | 0/1 | 180.9s |