Posts tagged with "benchmarks"
-
GPT-4.1: SWE improvements!
April 14, 2025 @ 12 PM
OpenAI’s GPT-4.1 sets new records on SWE-bench and Aider polyglot diff, while IDEs like Windsurf and Cursor roll out deep integrations—delivering smarter, faster, and more reliable coding for developers.
Read more →