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) |
|---|---|---|---|---|---|---|
| #30 | Step 3.5 Flash medium | Stepfun | 5.5 | 7.9 | 0/1 | 6.54s |
| #32 | Qwen3.5-Flash medium | Qwen | 6.1 | 7.8 | 0/1 | 40.1s |
| #36 | GPT-5.3 Chat none | OpenAI | 4.6 | 7.7 | 0/1 | 1.99s |
| #38 | GPT-5.4 Nano medium | OpenAI | 4.5 | 7.6 | 0/1 | 4.15s |
| #39 | Seed-2.0-Mini medium | Bytedance Seed | 5.1 | 7.5 | 0/1 | 36.7s |
| #40 | GPT-5.2 medium | OpenAI | 3.7 | 7.5 | 0/1 | 4.32s |
| #41 | MiMo-V2-Flash medium | Xiaomi | 4.0 | 7.5 | 0/1 | 4.20s |
| #42 | Claude Sonnet 4.6 none | Anthropic | 6.1 | 7.4 | 0/1 | 2.56s |
| #43 | Qwen3.5-35B-A3B medium | Qwen | 2.8 | 7.4 | 0/1 | 30.3s |
| #44 | GPT-5.4 Mini medium | OpenAI | 4.5 | 7.3 | 0/1 | 3.72s |
| #45 | GPT-5 Mini medium | OpenAI | 4.5 | 7.0 | 0/1 | 13.5s |
| #46 | Kimi K2.5 medium | Moonshot AI | 6.5 | 7.0 | 0/1 | 69.7s |
| #47 | Grok 4.20 medium | X AI | 5.8 | 7.0 | 0/1 | 7.09s |
| #49 | Qwen3.5 Plus 2026-02-15 none | Qwen | 4.4 | 6.8 | 0/1 | 2.26s |
| #50 | Hunter Alpha medium | OpenRouter | 7.0 | 6.7 | 0/1 | 6.44s |