Re:Testing AI coding agents on real codebases
by peggyrayzis on Tuesday August 12, 2025 @02:18PM
(#44879948)
Which one do you continue to reach for the most? I was surprised to see Gemini so low on your list even w/ the long context window.
[ Parent
| on HN ]
Re:Testing AI coding agents on real codebases
by aldersondev on Tuesday August 12, 2025 @04:46PM
(#44881624)
Hi there! Even though it didn't score the highest (Cursor did!), I loved Claude's code, it's the one that I'm still using after completing the testing! Anthropic got the UX right in my opinion!
Gemini surprised me, too! It was a mixed bag, as it performed well in the production tests but failed significantly on the control test. I bet as the model improves, it will quickly catch up, because that context window is a good feature!