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

Competitive Programming Agent Evaluation on ALE Bench

1,909.4Final Performance

Leeroo

788.9041,079.8021,370.71,661.598Jan 29, 2026
Updated 3mo ago

Evaluation Results

MethodLinks
2026.01
1,909.46.1914.8
2026.01
1,879.36.81,003.3
2026.01
1,19854.1111
2026.01
83288.44.7