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) |
|---|---|---|---|---|---|---|
| #48 | Gemma 4 31B none | 10.0 | 6.9 | 1/1 | 2.09s | |
| #77 | GLM 5 Turbo none | Z.ai | 4.2 | 5.5 | 0/1 | 2.18s |
| #58 | GLM 5V Turbo none | Z.ai | 4.6 | 6.2 | 0/1 | 2.22s |
| #49 | Qwen3.5 Plus 2026-02-15 none | Qwen | 4.4 | 6.8 | 0/1 | 2.26s |
| #65 | MiMo-V2-Pro none | Xiaomi | 4.3 | 6.0 | 0/1 | 2.44s |
| #67 | Qwen3.5-27B none | Qwen | 5.0 | 5.9 | 0/1 | 2.51s |
| #42 | Claude Sonnet 4.6 none | Anthropic | 6.1 | 7.4 | 0/1 | 2.56s |
| #72 | Hunter Alpha none | OpenRouter | 6.1 | 5.7 | 0/1 | 2.71s |
| #84 | gpt-oss-120b none | OpenAI | 4.6 | 5.2 | 0/1 | 2.83s |
| #78 | Trinity Large Preview none | Arcee AI | 4.4 | 5.3 | 0/1 | 2.86s |
| #64 | DeepSeek V3.2 none | DeepSeek | 10.0 | 6.1 | 1/1 | 2.86s |
| #35 | MiMo-V2-Omni medium | Xiaomi | 10.0 | 7.7 | 1/1 | 2.86s |
| #3 | Claude Opus 4.7 medium | Anthropic | 10.0 | 9.2 | 1/1 | 2.87s |
| #17 | Gemini 3.1 Flash Lite Preview medium | 10.0 | 8.2 | 1/1 | 3.16s | |
| #28 | GPT-5.2 Chat none | OpenAI | 4.4 | 7.9 | 0/1 | 3.20s |