SWE-bench · README.md source

swe

Results of cap-evolve runs on SWE-bench: SWE-bench and its variants (Verified, the Red Hat rh-swebench set). One of the per-benchmark result repos in the skillberry-runs org.

On the dashboard: https://skillberry-runs.github.io/dashboard/swe/. The run rows (reward, cost, models per run) are on the main table (filter Benchmark); each row's Open UI opens that run's CapEvolve dashboard from this repo's ci_ui/.

What is here

bench value in the run records runs
swebench 24
swebench-verified 3
rh-swebench 1

Adding to it

See the dashboard's PUBLISHING.md: section B for write-ups, F for "Open UI" data.