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

Software engineering agent task completion on SWE-Bench Verified

78.2Accuracy

LLM-as-a-Verifier

75.70476.3527777.648Jul 6, 2026
Updated 19d ago

Evaluation Results

MethodLinks
78.2--
2026.07
76.8--
2026.07
75.8--
2026.07
75.8--
-76.184.4