MiniMax官方发帖，scaling01发布模型数据
Official post from MiniMax. @scaling01 posted the numbers earlier tonight. https://t.co/PcgkBq8Zhu
Introducing MiniMax M3: The First Open-Weights Model to Combine Three Frontier Capabilities
- Coding & Agentic Frontier: 59.0% SWE-Bench Pro, 66.0% Terminal Bench 2.1, 34.8% SWE-fficiency, 28.8% KernelBench Hard, 74.2% MCP Atlas
- MiniMax Sparse Attention scales context to 1M
- https://t.co/TF891iJukF