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) |
|---|---|---|---|---|---|---|
| #130 | MiniMax M2.7 medium | Minimax | 3.9 | 5.3 | 0/1 | 38.7s |
| #131 | Qwen3.5-122B-A10B none | Qwen | 5.0 | 5.3 | 0/1 | 1.12s |
| #132 | Mistral Small 4 medium | Mistral | 4.8 | 5.3 | 0/1 | 2.05s |
| #133 | DeepSeek V3.2 none | DeepSeek | 4.7 | 5.2 | 0/1 | 9.32s |
| #134 | GLM 5 Turbo none | Z.ai | 4.2 | 5.2 | 0/1 | 2.18s |
| #136 | Elephant Alpha medium | Openrouter | 4.3 | 5.1 | 0/1 | 920ms |
| #137 | Elephant Alpha none | Openrouter | 4.0 | 5.1 | 0/1 | 854ms |
| #138 | Ling-2.6-flash none | Inclusionai | 4.0 | 5.0 | 0/1 | 1.45s |
| #139 | DeepSeek V4 Flash none | DeepSeek | 4.2 | 5.0 | 0/1 | 23.7s |
| #141 | Nemotron 3 Super none | NVIDIA | 4.6 | 4.9 | 0/1 | 950ms |
| #142 | Mistral Small 4 none | Mistral | 4.0 | 4.9 | 0/1 | 729ms |
| #143 | MiMo-V2.5 none | Xiaomi | 4.4 | 4.9 | 0/1 | 6.86s |
| #144 | GPT-5.4 Mini none | OpenAI | 4.8 | 4.9 | 0/1 | 1.82s |
| #145 | Laguna M.1 none | Poolside | 3.0 | 4.8 | 0/1 | 0ms |
| #146 | Laguna Xs.2 none | Poolside | 3.0 | 4.8 | 0/1 | 0ms |