Trik anti-AI: Jawaban salah
Trik anti-AI
Jawaban salah
Lihat model AI mana yang paling mungkin mengalami Jawaban salah di Trik anti-AI, agar Anda bisa menemukan titik lemahnya lebih cepat. Urutkan berdasarkan: Total Biaya ↓.
Model yang ditampilkan
15
Total kegagalan
502
Model yang paling terdampak
Grok 4.20 Multi Agent Beta 1Alasan kegagalan
249/249
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) |
|---|---|---|---|---|---|---|---|
| #391 | Grok 4.20 Multi Agent Beta medium | X AI | 1 | 0.7 | $5.599 | 2/4 | 3.46s |
| #185 | Step 5 Preview high | Stepfun | 1 | 0.7 | $4.513 | 2/4 | 14.7s |
| #271 | Step 5 Preview medium | Stepfun | 1 | 0.6 | $4.136 | 2/4 | 12.6s |
| #302 | Step 5 Preview low | Stepfun | 1 | 0.7 | $4.110 | 2/4 | 9.50s |
| #105 | Claude Opus 4.7 medium | Anthropic | 1 | 0.8 | $3.636 | 3/4 | 1.85s |
| #175 | Claude Opus 5 none | Anthropic | 3 | 0.6 | $2.766 | 1/4 | 4.33s |
| #87 | Muse Spark 1.1 high | Meta | 1 | 0.7 | $2.570 | 2/4 | 8.60s |
| #60 | GPT-5.4 medium | OpenAI | 1 | 0.8 | $2.213 | 3/4 | 4.11s |
| #236 | Claude Sonnet 4.6 medium | Anthropic | 1 | 0.7 | $2.126 | 2/4 | 2.98s |
| #366 | Gemini 3.1 Flash Lite high | 1 | 0.9 | $2.044 | 3/4 | 37.2s | |
| #68 | Seed 2.1 Turbo medium | Bytedance Seed | 1 | 0.8 | $2.042 | 3/4 | 28.2s |
| #42 | Seed 2.1 Turbo high | Bytedance Seed | 1 | 0.8 | $1.892 | 3/4 | 47.0s |
| #58 | Pareto 26.9 default | Unbiased | 2 | 0.7 | $1.864 | 2/4 | 6.44s |
| #317 | Hy4 preview low | Tencent | 4 | 0.6 | $1.844 | 0/4 | 129.6s |
| #29 | Seed 2.1 Turbo low | Bytedance Seed | 1 | 0.8 | $1.645 | 3/4 | 34.8s |