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

Contextual Reasoning on BigBenchHard

63.23EM

Sigma-MoE-Tiny Base

40.599646.474852.3558.2252Dec 18, 2025
Updated 1mo ago

Evaluation Results

MethodLinks
2025.12
63.23
2025.12
51.7
2025.12
44.1
2025.12
41.47