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: Kipimo ↑.
| Nafasi | Modeli | Kampuni | Alama ya Akili ya jumla | Alama | Majaribio sahihi | Muda wa majibu (wastani) |
|---|---|---|---|---|---|---|
| #85 | Elephant none | Openrouter | 4.0 | 5.2 | 0/1 | 854ms |
| #89 | GPT-4o-mini none | OpenAI | 4.0 | 4.9 | 0/1 | 909ms |
| #98 | LFM2-24B-A2B none | Liquid | 4.0 | 4.1 | 0/1 | 395ms |
| #57 | GPT-5 Nano medium | OpenAI | 4.1 | 6.3 | 0/1 | 17.5s |
| #52 | Grok 4.1 Fast medium | X AI | 4.2 | 6.7 | 0/1 | 16.2s |
| #77 | GLM 5 Turbo none | Z.ai | 4.2 | 5.5 | 0/1 | 2.18s |
| #88 | Nemotron 3 Super none | NVIDIA | 4.2 | 5.1 | 0/1 | 25.0s |
| #68 | gpt-oss-120b medium | OpenAI | 4.3 | 5.8 | 0/1 | 7.90s |
| #81 | Elephant medium | Openrouter | 4.3 | 5.2 | 0/1 | 920ms |
| #65 | MiMo-V2-Pro none | Xiaomi | 4.3 | 6.0 | 0/1 | 2.44s |
| #28 | GPT-5.2 Chat none | OpenAI | 4.4 | 7.9 | 0/1 | 3.20s |
| #49 | Qwen3.5 Plus 2026-02-15 none | Qwen | 4.4 | 6.8 | 0/1 | 2.26s |
| #66 | GPT-5.4 none | OpenAI | 4.4 | 5.9 | 0/1 | 1.78s |
| #78 | Trinity Large Preview none | Arcee AI | 4.4 | 5.3 | 0/1 | 2.86s |
| #90 | Qwen3.5-9B none | Qwen | 4.4 | 4.8 | 0/1 | 552ms |