Kategoria ya AI BENCHY
Orodha ya Akili ya jumla
Ona ni modeli gani za AI zinafanya vizuri zaidi katika Akili ya jumla, zipi zinabaki thabiti, na pengo kubwa liko wapi. Panga kwa: Muda wa majibu (wastani) ↑.
| Nafasi | Modeli | Kampuni | Alama ya Akili ya jumla | Alama | Majaribio sahihi | Muda wa majibu (wastani) |
|---|---|---|---|---|---|---|
| #100 | Grok Build 0.1 none | X AI | 4.3 | 6.0 | 0/1 | 12.5s |
| #104 | Nemotron 3 Ultra 550b A55b none | NVIDIA | 5.0 | 6.0 | 0/1 | 13.5s |
| #54 | GPT-5 Mini medium | OpenAI | 4.5 | 7.3 | 0/1 | 13.5s |
| #83 | Step 3.5 Flash none | Stepfun | 4.0 | 6.6 | 0/1 | 14.4s |
| #17 | GLM 5 medium | Z.ai | 6.1 | 8.3 | 0/1 | 14.7s |
| #96 | Ring-2.6-1T none | Inclusionai | 4.3 | 6.2 | 0/1 | 15.6s |
| #156 | Hy3 preview none | Tencent | 4.1 | 4.4 | 0/1 | 16.1s |
| #86 | Grok 4.1 Fast medium | X AI | 4.2 | 6.5 | 0/1 | 16.2s |
| #33 | Hy3 preview medium | Tencent | 10.0 | 7.7 | 1/1 | 16.8s |
| #94 | GPT-5 Nano medium | OpenAI | 4.1 | 6.3 | 0/1 | 17.5s |
| #60 | Kimi K2.6 medium | Moonshot AI | 10.0 | 7.2 | 1/1 | 17.8s |
| #158 | GLM 4.7 Flash medium | Z.ai | 3.6 | 4.4 | 0/1 | 18.1s |
| #19 | Seed-2.0-Lite medium | Bytedance Seed | 6.7 | 8.2 | 0/1 | 18.2s |
| #47 | Grok Build 0.1 medium | X AI | 4.4 | 7.4 | 0/1 | 18.4s |
| #159 | Ling-2.6-1T none | Inclusionai | 5.0 | 4.3 | 0/1 | 20.3s |