Peringkat Tugas agen
Lihat model AI mana yang paling baik di Tugas agen, mana yang tetap andal, dan di mana kesenjangan terbesar muncul. Urutkan berdasarkan: Tes benar ↑.
380/380
Filter model
Tidak ada model yang cocok dengan pencarian dan filter saat ini.
| Peringkat | Model | Perusahaan | Skor Tugas agen | Skor | Total Biaya | Tes benar | Waktu respons (rata-rata) |
|---|---|---|---|---|---|---|---|
| #310 | Hy4 preview none | Tencent | 5.0 | 4.9 | $0.161 | 0/1 | 65.5s |
| #311 | Mimo V2 Omni medium | Xiaomi | 0.0 | 4.9 | $0.683 | 0/0 | 0ms |
| #312 | Hy3 preview high | Tencent | 0.0 | 4.8 | $0.135 | 0/0 | 0ms |
| #313 | GLM 4.7 Flash none | Z.ai | 5.0 | 4.8 | $0.027 | 0/1 | 80.7s |
| #314 | Mercury 2.5 Preview none | Inception | 3.9 | 4.7 | $0.023 | 0/1 | 85.0s |
| #315 | Nemotron 3.5 Lightning medium | NVIDIA | 2.8 | 4.7 | $0.129 | 0/1 | 341.8s |
| #316 | North Mini Code none | Cohere | 3.0 | 4.7 | $0.000 | 0/1 | 18.9s |
| #317 | Laguna S 2.1 none | Poolside | 5.4 | 4.7 | $0.047 | 0/1 | 149.3s |
| #318 | Granite 4.2 8B high | IBM Granite | 5.0 | 4.7 | $0.161 | 0/1 | 223.5s |
| #319 | Qwen3 Coder Next medium | Qwen | 5.0 | 4.7 | $0.069 | 0/1 | 151.4s |
| #320 | DeepSeek V3.2 none | DeepSeek | 3.0 | 4.6 | $0.121 | 0/1 | 122.5s |
| #321 | GPT-5.4 Nano none | OpenAI | 3.9 | 4.6 | $0.068 | 0/1 | 45.4s |
| #322 | Gemini 3.1 Flash Lite high | 0.0 | 4.6 | $2.044 | 0/0 | 0ms | |
| #323 | GLM 5V Turbo none | Z.ai | 0.0 | 4.6 | $0.052 | 0/0 | 0ms |
| #324 | Laguna S 2.1 low | Poolside | 2.8 | 4.6 | $0.109 | 0/1 | 152.1s |