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 ↓.
Modeli zilizoonyeshwa
15
Wastani wa Alama ya Akili ya jumla
5.9
Modeli bora
Gemini 3 Flash Preview 10.0| Nafasi | Modeli | Kampuni | Alama ya Akili ya jumla | Alama | Majaribio sahihi | Muda wa majibu (wastani) |
|---|---|---|---|---|---|---|
| #22 | Step 3.7 Flash medium | Stepfun | 4.0 | 8.0 | 0/1 | 6.85s |
| #23 | GLM 5 Turbo medium | Z.ai | 6.1 | 8.0 | 0/1 | 10.1s |
| #24 | GPT-5.2 Chat none | OpenAI | 4.4 | 7.9 | 0/1 | 3.20s |
| #25 | Qwen3.5 Plus 2026-02-15 medium | Qwen | 4.7 | 7.9 | 0/1 | 79.9s |
| #26 | Qwen3.6 Plus medium | Qwen | 5.1 | 7.9 | 0/1 | 27.1s |
| #28 | Gemini 2.5 Flash medium | 4.8 | 7.8 | 0/1 | 4.86s | |
| #29 | Qwen3.5-122B-A10B medium | Qwen | 3.4 | 7.8 | 0/1 | 34.1s |
| #30 | Qwen3.5-27B medium | Qwen | 6.1 | 7.8 | 0/1 | 101.4s |
| #31 | DeepSeek V4 Flash high | DeepSeek | 6.1 | 7.7 | 0/1 | 25.2s |
| #36 | Qwen3.5 Plus 2026-04-20 medium | Qwen | 4.9 | 7.6 | 0/1 | 25.3s |
| #38 | Grok 4.3 medium | X AI | 5.4 | 7.6 | 0/1 | 24.7s |
| #39 | Qwen3.6 Flash medium | Qwen | 4.8 | 7.5 | 0/1 | 9.88s |
| #41 | Nemotron 3 Ultra 550b A55b medium | NVIDIA | 3.7 | 7.5 | 0/1 | 2.52s |
| #42 | GPT-5.2 medium | OpenAI | 3.7 | 7.5 | 0/1 | 4.32s |
| #43 | MiMo-V2.5-Pro medium | Xiaomi | 5.5 | 7.5 | 0/1 | 4.02s |