Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Software Engineering Tasks on SWE-bench Multilingual (test)

77.8Resolution Rate (%)

Claude Opus 4.6

69.89671.9487476.052Mar 29, 2026
Updated 19d ago

Evaluation Results

MethodLinks
2026.03
77.8
2026.03
75.4
2026.03
71.2
2026.03
70.2