Kategori AI BENCHY
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: Tes benar ↑.
| Peringkat | Model | Perusahaan | Skor Pemanggilan alat | Skor | Tes benar | Waktu respons (rata-rata) |
|---|---|---|---|---|---|---|
| #13 | Grok 4.20 Beta medium | X AI | 3.0 | 8.5 | 0/1 | 12.4s |
| #20 | Gemini 3.5 Flash none | 3.0 | 8.1 | 0/1 | 0ms | |
| #27 | Gemma 4 31B medium | 3.0 | 7.8 | 0/1 | 0ms | |
| #42 | GPT-5.2 medium | OpenAI | 4.7 | 7.5 | 0/1 | 10.3s |
| #45 | GPT-5.4 Mini medium | OpenAI | 4.7 | 7.5 | 0/1 | 9.62s |
| #46 | Qwen3.6 35B A3B medium | Qwen | 3.0 | 7.4 | 0/1 | 0ms |
| #55 | GLM 5.1 medium | Z.ai | 3.0 | 7.3 | 0/1 | 0ms |
| #59 | GLM 5V Turbo medium | Z.ai | 7.0 | 7.2 | 0/1 | 12.5s |
| #65 | Grok 4.20 medium | X AI | 3.0 | 7.1 | 0/1 | 13.7s |
| #83 | Step 3.5 Flash none | Stepfun | 3.0 | 6.6 | 0/1 | 0ms |
| #84 | Grok 4.20 Multi Agent Beta medium | X AI | 3.0 | 6.6 | 0/1 | 0ms |
| #85 | Gemma 4 31B none | 3.0 | 6.5 | 0/1 | 0ms | |
| #86 | Grok 4.1 Fast medium | X AI | 2.8 | 6.5 | 0/1 | 27.7s |
| #89 | Hy3 preview low | Tencent | 2.8 | 6.4 | 0/1 | 17.8s |
| #96 | Ring-2.6-1T none | Inclusionai | 3.0 | 6.2 | 0/1 | 0ms |