Comment Comment by molticrystal Their code and evalations are linked to on the blog post accompanying the results:Blog Post: https://runta.com/blog/introducing-frontierharness-eval/The tasks and methodology: https://github.com/runta-dev/frontier-harness-eval parent molticrystal 1 month ago
Blog Post: https://runta.com/blog/introducing-frontierharness-eval/
The tasks and methodology: https://github.com/runta-dev/frontier-harness-eval