13 Models and 4 Agents on SWE Tasks: Go, Java, Python, Rust, TS

iibragim_bad about 2 hours ago 1 commentsRead Article on swe-rebench.com

DE version is available. Content is displayed in original English for accuracy.

Discussion (1 Comments)Read Original on HackerNews

spullara•about 1 hour ago

They are all different problems for the different languages. I was hoping this was a benchmark that attempted to see which languages were more efficient to use with which models.