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) |
|---|---|---|---|---|---|---|
| #70 | Qwen3.5-122B-A10B none | Qwen | 5.0 | 5.7 | 0/1 | 1.12s |
| #21 | Gemini 3 Flash Preview none | 10.0 | 8.1 | 1/1 | 1.13s | |
| #55 | MiMo-V2-Omni none | Xiaomi | 4.5 | 6.5 | 0/1 | 1.19s |
| #63 | Qwen3.5-35B-A3B none | Qwen | 6.5 | 6.1 | 0/1 | 1.19s |
| #96 | GPT-5.4 Nano none | OpenAI | 3.8 | 4.5 | 0/1 | 1.31s |
| #87 | Qwen3 Coder Next none | Qwen | 10.0 | 5.1 | 1/1 | 1.34s |
| #92 | Qwen3 Coder Next medium | Qwen | 6.3 | 4.7 | 0/1 | 1.39s |
| #22 | Gemini 3.1 Flash Lite Preview low | 4.0 | 8.1 | 0/1 | 1.54s | |
| #69 | Kimi K2.6 none | Moonshot AI | 5.4 | 5.8 | 0/1 | 1.55s |
| #74 | GLM 4.7 Flash none | Z.ai | 4.0 | 5.6 | 0/1 | 1.59s |
| #94 | MiMo-V2-Flash none | Xiaomi | 4.6 | 4.5 | 0/1 | 1.67s |
| #66 | GPT-5.4 none | OpenAI | 4.4 | 5.9 | 0/1 | 1.78s |
| #86 | GPT-5.4 Mini none | OpenAI | 4.8 | 5.1 | 0/1 | 1.82s |
| #36 | GPT-5.3 Chat none | OpenAI | 4.6 | 7.7 | 0/1 | 1.99s |
| #73 | Mistral Small 4 medium | Mistral | 4.8 | 5.7 | 0/1 | 2.05s |