Kegagalan kategori AI BENCHY
Spesifik domain: Jawaban salah
Spesifik domain
Jawaban salah
Lihat model AI mana yang paling mungkin mengalami Jawaban salah di Spesifik domain, agar Anda bisa menemukan titik lemahnya lebih cepat. Urutkan berdasarkan: Jumlah kegagalan ↑.
Alasan kegagalan
| Peringkat | Model | Perusahaan | Jumlah Jawaban salah | Skor kategori | Tes benar | Waktu respons (rata-rata) |
|---|---|---|---|---|---|---|
| #2 | Gemini 3.1 Pro Preview medium | 1 | 7.7 | 2/3 | 32.7s | |
| #4 | Claude Opus 4.7 none | Anthropic | 1 | 7.7 | 2/3 | 1.19s |
| #8 | Qwen3.5 Plus 2026-02-15 medium | Qwen | 1 | 5.3 | 1/3 | 17.5s |
| #10 | Qwen3.5-27B medium | Qwen | 1 | 5.3 | 1/3 | 79.5s |
| #14 | Gemma 4 31B medium | 1 | 7.7 | 2/3 | 38.5s | |
| #21 | Gemini 3 Flash Preview none | 1 | 7.7 | 2/3 | 963ms | |
| #23 | MiMo-V2-Pro medium | Xiaomi | 1 | 5.3 | 1/3 | 6.00s |
| #26 | Claude Sonnet 4.6 medium | Anthropic | 1 | 2.9 | 0/3 | 0ms |
| #27 | DeepSeek V3.2 medium | DeepSeek | 1 | 5.3 | 1/3 | 39.3s |
| #32 | Qwen3.5-Flash medium | Qwen | 1 | 5.3 | 1/3 | 146.5s |
| #33 | GLM 5.1 medium | Z.ai | 1 | 5.3 | 1/3 | 29.8s |
| #35 | MiMo-V2-Omni medium | Xiaomi | 1 | 3.0 | 0/3 | 55.1s |
| #37 | Claude Opus 4.6 medium | Anthropic | 1 | 3.0 | 0/3 | 83.4s |
| #40 | GPT-5.2 medium | OpenAI | 1 | 5.9 | 1/3 | 77.8s |
| #42 | Claude Sonnet 4.6 none | Anthropic | 1 | 7.7 | 2/3 | 3.54s |