Get the latest tech news

Microsoft's MAI-Code-1-Flash Scores 51% SWE-Bench Pro with Just 5B Active Params


g task reasoning Agentic execution Broad programming language support Fluent across programming languages, frameworks, and ecosystems. Optimized for GitHub Copilot in VS Code Performance SWE-Bench Pro 0 % Coding capabilities AIME 2026 0 % Math performance IFBench 0 % Instruction following Dig Deeper Try MAI-Code-1-Flash GitHub Copilot in Visual Studio Code From strategy to shipped code, keep every project moving forward..

None

Get the Android app

Or read this on Hacker News

Read more on:

Photo of Microsoft

Microsoft

Photo of Bench

Bench

Photo of Pro

Pro

Related news:

News photo

I saw the first Nvidia RTX Spark laptops - these 4 models will lead the new ultrabook boom

News photo

Microsoft's first reasoning model is one of 7 AIs just released at Build - what we know so far

News photo

Microsoft insists Defender is enough for most PCs, but admits third‑party antivirus tools still offer extras it can’t match