SWEBench Score Discrepency
- two failures because ...
# dev-pr-reviews
strong-ice-84145
12/11/2025, 3:56 PMSWEBench Score Discrepency
• two failures because of missing package. Simple fix https://github.com/OpenHands/benchmarks/pull/154
• two failures because modal crashes silently. Issue https://github.com/OpenHands/benchmarks/issues/155
@chilly-france-44439 @millions-crayon-32880 FYI
✅ 1
c
chilly-france-44439
12/11/2025, 8:07 PMapproved the first one
chilly-france-44439
12/11/2025, 8:07 PMfor 2nd one, left a comment: https://github.com/OpenHands/benchmarks/issues/155#issuecomment-3643596685