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

Agentic task on VitaBench Delivery

30.74Avg@2

Snapshot

18.634421.777224.9228.0628May 12, 2026
Updated 21d ago

Evaluation Results

MethodLinks
2026.05
30.7445
2026.05
28.4943
2026.05
27.3342
2026.05
25.8839
2026.05
25.8839
2026.05
20.7433
2026.05
19.5633
2026.05
19.128