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: Majaribio sahihi ↑.
| Nafasi | Modeli | Kampuni | Alama ya Akili ya jumla | Alama | Majaribio sahihi | Muda wa majibu (wastani) |
|---|---|---|---|---|---|---|
| #114 | Qwen3.5 Plus 2026-04-20 none | Qwen | 4.8 | 5.7 | 0/1 | 1.41s |
| #115 | Qwen3.5-27B none | Qwen | 5.0 | 5.7 | 0/1 | 2.51s |
| #116 | Hunter Alpha none | OpenRouter | 6.1 | 5.7 | 0/1 | 2.71s |
| #117 | Qwen3.5-35B-A3B none | Qwen | 6.5 | 5.6 | 0/1 | 1.19s |
| #118 | Qwen3.6 27B none | Qwen | 5.2 | 5.6 | 0/1 | 1.07s |
| #119 | Cobuddy medium | Baidu | 4.2 | 5.6 | 0/1 | 23.2s |
| #120 | Mimo V2 PRO none | Xiaomi | 4.3 | 5.6 | 0/1 | 2.44s |
| #121 | Owl Alpha none | Openrouter | 4.3 | 5.5 | 0/1 | 4.61s |
| #122 | GLM 4.7 Flash none | Z.ai | 4.0 | 5.5 | 0/1 | 1.59s |
| #123 | MiMo-V2.5-Pro none | Xiaomi | 4.0 | 5.5 | 0/1 | 2.58s |
| #124 | Kimi K2.6 none | Moonshot AI | 5.4 | 5.5 | 0/1 | 1.55s |
| #125 | GPT-5.4 none | OpenAI | 4.4 | 5.5 | 0/1 | 1.78s |
| #126 | gpt-oss-120b none | OpenAI | 4.8 | 5.4 | 0/1 | 10.8s |
| #127 | Grok 4.20 none | X AI | 4.8 | 5.4 | 0/1 | 659ms |
| #129 | MiniMax M2.5 medium | Minimax | 3.8 | 5.3 | 0/1 | 6.63s |