mirror of
https://github.com/priyanshujain/messageboardbench.git
synced 2026-10-02 11:07:07 +00:00
SWE-bench baseline
Three no-communication model populations on the same 20 conflicting SWE tasks. See DESIGN.md for the frozen design and analysis.md for reviewed results.
Infrastructure recovery is recorded in recovery.md. The selected scored results and automatic report are in logs/baseline-swebench/.