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

Multi-Task Reasoning on MMLU

56.7Pass@1

DCRL

32.98839.14445.351.456Mar 17, 2026
Updated 2mo ago

Evaluation Results

MethodLinks
2026.03
56.7
2026.03
52.6
2026.03
33.9