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

Agentic Coding on SWE-Bench (Score, Relative Change)

59Score

SAR

56.50457.15257.858.448Jul 3, 2026
Updated 18d ago

Evaluation Results

MethodLinks
2026.07
591.72
2026.07
58-
2026.07
57.41.41
2026.07
56.6-