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

Placement on 100-task benchmark (test)

0PE (cm)

Ground Truth (GT)

-0.1240.7131.552.387Jun 12, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
0-100
2026.06
1.2-96
2026.06
1.89487
2026.06
2.29184
2026.06
2.48982
2026.06
2.68982
2026.06
2.88780
2026.06
3.18578