Peringkat Pemanggilan alat
Lihat model AI mana yang paling baik di Pemanggilan alat, mana yang tetap andal, dan di mana kesenjangan terbesar muncul. Urutkan berdasarkan: Total Biaya ↓.
Model yang ditampilkan
15
Rata-rata Skor Pemanggilan alat
8.8
Model terbaik
Grok 4.20 Multi Agent Beta 3.0
330/330
Filter model
Tidak ada model yang cocok dengan pencarian dan filter saat ini.
| Peringkat | Model | Perusahaan | Skor Pemanggilan alat | Skor | Total Biaya | Tes benar | Waktu respons (rata-rata) |
|---|---|---|---|---|---|---|---|
| #182 | Hy3 preview medium | Tencent | 10.0 | 6.5 | $0.049 | 1/1 | 15.0s |
| #241 | KAT-Coder-Air V2.5 medium | Kwaipilot | 10.0 | 5.6 | $0.048 | 1/1 | 4.77s |
| #197 | Gemini 3.1 Flash Lite minimal | 10.0 | 6.1 | $0.047 | 1/1 | 3.51s | |
| #274 | GLM 5 Turbo none | Z.ai | 10.0 | 5.1 | $0.047 | 1/1 | 8.21s |
| #201 | Gemini 3.1 Flash Lite none | 10.0 | 6.1 | $0.046 | 1/1 | 2.97s | |
| #251 | KAT-Coder-Air V2.5 low | Kwaipilot | 10.0 | 5.4 | $0.046 | 1/1 | 4.47s |
| #127 | DeepSeek V4 Flash 0731 medium | DeepSeek | 10.0 | 7.3 | $0.046 | 1/1 | 4.41s |
| #239 | Mimo V2 PRO none | Xiaomi | 10.0 | 5.6 | $0.045 | 1/1 | 4.39s |
| #187 | LongCat 2.0 none | Meituan | 10.0 | 6.4 | $0.044 | 1/1 | 6.64s |
| #192 | MiMo-V2-Flash medium | Xiaomi | 10.0 | 6.3 | $0.043 | 1/1 | 27.8s |
| #133 | Qwen3.7 Flash low | Qwen | 10.0 | 7.2 | $0.043 | 1/1 | 7.66s |
| #245 | Hy3 preview low | Tencent | 2.8 | 5.5 | $0.042 | 0/1 | 17.8s |
| #97 | DeepSeek V4 Flash 0423 high | DeepSeek | 10.0 | 7.6 | $0.042 | 1/1 | 74.7s |
| #288 | GPT-5.4 Nano none | OpenAI | 10.0 | 4.8 | $0.041 | 1/1 | 3.40s |
| #285 | Hy4 preview none | Tencent | 3.0 | 4.8 | $0.041 | 0/1 | 81.5s |