feat(evaluation): Add multi-swe-bench dependency and fix rollout script (#11326)

Co-authored-by: Graham Neubig <neubig@gmail.com>
2026-01-09 14:57:59 -05:00 · 2025-10-16 07:35:19 -07:00
parent f42a4f75cb
commit a237b578c0
3 changed files with 37 additions and 16 deletions
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -186,6 +186,7 @@ pyarrow = "21.0.0"
 datasets = "*"
 joblib = "*"
 swebench = { git = "https://github.com/ryanhoangt/SWE-bench.git", rev = "fix-modal-patch-eval" }
+multi-swe-bench = "0.1.2"

 [tool.poetry.scripts]
 openhands = "openhands.cli.entry:main"