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) |
|---|---|---|---|---|---|---|
| #32 | MiMo-V2-Omni medium | Xiaomi | 1 | 4.0 | 0/1 | 68.5s |
| #54 | GPT-5 Nano medium | OpenAI | 1 | 6.7 | 0/1 | 40.7s |
| #74 | Trinity Large Preview none | Arcee AI | 1 | 6.3 | 0/1 | 39.5s |
| #69 | Mistral Small 4 medium | Mistral | 1 | 6.7 | 0/1 | 30.5s |
| #65 | gpt-oss-120b medium | OpenAI | 1 | 4.3 | 0/1 | 26.3s |
| #44 | Grok 4.20 medium | X AI | 1 | 4.3 | 0/1 | 24.3s |
| #71 | GLM 5.1 none | Z.ai | 1 | 5.1 | 0/1 | 9.79s |
| #79 | gpt-oss-120b none | OpenAI | 1 | 4.3 | 0/1 | 9.57s |
| #50 | GLM 5 none | Z.ai | 1 | 5.6 | 0/1 | 8.84s |
| #61 | DeepSeek V3.2 none | DeepSeek | 1 | 2.4 | 0/1 | 7.63s |
| #84 | Qwen3.5-9B none | Qwen | 1 | 5.2 | 0/1 | 5.69s |
| #70 | GLM 4.7 Flash none | Z.ai | 1 | 6.4 | 0/1 | 5.57s |
| #73 | GLM 5 Turbo none | Z.ai | 1 | 5.3 | 0/1 | 3.93s |
| #46 | Qwen3.5 Plus 2026-02-15 none | Qwen | 1 | 6.3 | 0/1 | 3.63s |
| #66 | Qwen3.5-122B-A10B none | Qwen | 1 | 4.3 | 0/1 | 3.44s |