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

Competitive Coding on OJBench

45.9Best@8 Score

Agentic Verifier

28.01232.65637.341.944Feb 4, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.02
45.948.6
2026.02
43.844.2
2026.02
4140.6
2026.02
40.541.4
2026.02
40.439.5
2026.02
37.739.6
2026.02
37.634.9
2026.02
37.137.1
2026.02
33.534.9
2026.02
33.434.1
2026.02
3231.3
2026.02
31.632.1
2026.02
31.431.8
2026.02
29.632.4
2026.02
28.928.9
2026.02
28.729.3