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: Total Biaya ↓.
Alasan kegagalan
134/134
Filter model
Tidak ada model yang cocok dengan pencarian dan filter saat ini.
| Peringkat | Model | Perusahaan | Jumlah Jawaban salah | Skor kategori | Total Biaya | Tes benar | Waktu respons (rata-rata) |
|---|---|---|---|---|---|---|---|
| #12 | GPT-5.5 medium | OpenAI | 1 | 8.8 | $3.679 | 2/3 | 59.8s |
| #26 | Grok 4.5 medium | X AI | 1 | 7.6 | $1.696 | 2/3 | 155.7s |
| #38 | Claude Sonnet 4.6 medium | Anthropic | 1 | 5.7 | $1.418 | 1/3 | 33.3s |
| #45 | Claude Opus 4.8 low | Anthropic | 1 | 6.6 | $1.270 | 1/3 | 7.58s |
| #20 | GPT-5.4 medium | OpenAI | 1 | 8.8 | $1.210 | 2/3 | 44.4s |
| #75 | Step 3.7 Flash high | Stepfun | 1 | 4.0 | $1.148 | 0/3 | 206.2s |
| #79 | Gemini 3.5 Flash none | 1 | 8.8 | $1.079 | 2/3 | 34.7s | |
| #10 | Gemini 3.1 Pro Preview medium | 1 | 7.9 | $1.054 | 2/3 | 40.2s | |
| #14 | Qwen3.6 Max Preview medium | Qwen | 1 | 8.8 | $0.960 | 2/3 | 146.5s |
| #53 | Grok Build 0.1 medium | X AI | 1 | 5.7 | $0.927 | 1/3 | 108.5s |
| #50 | GPT-5.6 Luna high | OpenAI | 2 | 5.5 | $0.924 | 1/3 | 15.6s |
| #29 | GPT-5.6 Terra high | OpenAI | 1 | 7.6 | $0.852 | 2/3 | 9.14s |
| #86 | Mimo V2 Omni medium | Xiaomi | 1 | 3.3 | $0.683 | 0/3 | 183.9s |
| #16 | Claude Opus 4.7 medium | Anthropic | 1 | 7.6 | $0.679 | 2/3 | 13.0s |
| #2 | Gemini 3 Flash Preview medium | 1 | 8.6 | $0.667 | 2/3 | 84.4s |