WHAT NEW IN X10.28 WED

X 上的 AI 合集档案 · 22 个合集 · 58,924 条

minimax-m3.1THREAD

BuildingBench 3D 榜:M3.1 Flash 73.3 分排第 12,超 SWE-2

EnactraAI 给出 BuildingBench 数据:MiniMax M3.1 Flash 综合 73.3 排第 12,高于 SWE-2 的 67.3,接近 DeepSeek V4.1 Flash 的 72.9,最佳重建单项 88.8。

Enactra AI
@EnactraAI7 天前收录原推发布于 2026.10.20
THREAD作者分 2 层发完
  1. MiniMax M3.1 Flash reshapes BuildingBench’s cost–quality frontier! Another open model making moves in 3D 🏗️🔥 🎈 73.3 overall, ranking #12. 🎈 Above SWE-2’s 67.3, taking its place on the Pareto frontier. 🎈 Close to the previous DeepSeek V4.1 Flash’s 72.9—and currently free through OpenRouter! Its best reconstruction hits 88.8 on Melbourne’s Australian Centre for Contemporary Art. How does it look alongside DeepSeek V4.1 Flash 1017 and #1 Opus 5.5? Comparison video below 👇

  2. Now for the buildings behind the bars 👀 MiniMax M3.1 Flash 🆚 DeepSeek V4.1 Flash 1017 🆚 Opus 5.5—all at max effort. Their overall BuildingBench scores: 73.3 🆚 81.9 🆚 86.8. MiniMax still has ground to cover, but this is an exciting start for an open model you can currently try for free. Where do you see the biggest differences in geometry and detail? https://buildingbench.enactra.ai/

Enactra AI @EnactraAI原推发布于 2026.10.20
在 X 上打开原推
x.com/enactraai/status/2112285793981235490采集于 2026.10.20 20:14