Peringkat Kepatuhan instruksi
Lihat model AI mana yang paling baik di Kepatuhan instruksi, mana yang tetap andal, dan di mana kesenjangan terbesar muncul.
461/461
Filter model
Tidak ada model yang cocok dengan pencarian dan filter saat ini.
| Peringkat | Model | Perusahaan | Skor Kepatuhan instruksi | Skor | Total Biaya | Tes benar | Waktu respons (rata-rata) |
|---|---|---|---|---|---|---|---|
| #62 | Muse Spark 1.1 medium | Meta | 0.7 | 0.9 | $1.665 | 1/2 | 6.31s |
| #143 | Muse Wonder high | Meta | 0.7 | 0.8 | $3.426 | 1/2 | 1.97s |
| #151 | Muse Wonder xhigh | Meta | 0.7 | 0.8 | $4.012 | 1/2 | 2.64s |
| #174 | LongCat 2.0 high | Meituan | 0.7 | 0.7 | $0.778 | 1/2 | 6.96s |
| #183 | LongCat 2.0 medium | Meituan | 0.7 | 0.7 | $0.767 | 1/2 | 7.38s |
| #231 | LongCat 2.0 low | Meituan | 0.7 | 0.7 | $0.630 | 1/2 | 6.39s |
| #240 | Mercury 2.5 high | Inception | 0.7 | 0.6 | $0.044 | 1/2 | 934ms |
| #260 | LongCat 2.0 none | Meituan | 0.7 | 0.6 | $0.104 | 1/2 | 2.82s |
| #274 | DeepSeek V4 Flash 0423 none | DeepSeek | 0.7 | 0.6 | $0.149 | 1/2 | 17.5s |
| #281 | Claude Fable 5.1 low | Anthropic | 0.7 | 0.6 | $3.395 | 1/2 | 5.24s |
| #292 | Claude Sonnet 4.6 none | Anthropic | 0.7 | 0.6 | $0.661 | 1/2 | 1.96s |
| #305 | DeepSeek V4.1 Flash 1017 none | DeepSeek | 0.7 | 0.6 | $0.055 | 1/2 | 608ms |
| #307 | DeepSeek V4.1 Flash none | DeepSeek | 0.7 | 0.6 | $0.391 | 1/2 | 6.81s |
| #313 | Mistral Large 4 none | Mistral | 0.7 | 0.6 | $0.290 | 1/2 | 1.16s |
| #316 | Gemma 4 31B none | 0.7 | 0.6 | $0.031 | 1/2 | 2.84s |