Kategoria ya AI BENCHY
Orodha ya Mbinu za kupinga AI
Ona ni modeli gani za AI zinafanya vizuri zaidi katika Mbinu za kupinga AI, zipi zinabaki thabiti, na pengo kubwa liko wapi. Panga kwa: Kipimo ↑.
| Nafasi | Modeli | Kampuni | Alama ya Mbinu za kupinga AI | Alama | Majaribio sahihi | Muda wa majibu (wastani) |
|---|---|---|---|---|---|---|
| #41 | Nemotron 3 Ultra 550b A55b medium | NVIDIA | 10.0 | 7.5 | 4/4 | 8.62s |
| #43 | MiMo-V2.5-Pro medium | Xiaomi | 10.0 | 7.5 | 4/4 | 3.26s |
| #46 | Qwen3.6 35B A3B medium | Qwen | 10.0 | 7.4 | 4/4 | 6.02s |
| #49 | Qwen3.5-Flash medium | Qwen | 10.0 | 7.4 | 4/4 | 59.1s |
| #51 | Mimo V2 PRO medium | Xiaomi | 10.0 | 7.4 | 4/4 | 2.86s |
| #55 | GLM 5.1 medium | Z.ai | 10.0 | 7.3 | 4/4 | 8.31s |
| #56 | MiMo-V2.5 medium | Xiaomi | 10.0 | 7.3 | 4/4 | 4.14s |
| #62 | Step 3.5 Flash medium | Stepfun | 10.0 | 7.2 | 4/4 | 40.6s |
| #66 | Qwen3.5-35B-A3B medium | Qwen | 10.0 | 7.1 | 4/4 | 21.1s |
| #71 | Step 3.7 Flash high | Stepfun | 10.0 | 7.0 | 4/4 | 13.4s |
| #75 | Ring-2.6-1T medium | Inclusionai | 10.0 | 6.9 | 4/4 | 42.2s |
| #80 | Mimo V2 Omni medium | Xiaomi | 10.0 | 6.7 | 4/4 | 2.75s |
| #83 | Step 3.5 Flash none | Stepfun | 10.0 | 6.6 | 4/4 | 35.0s |