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

Long-context Memory Evaluation on LoCoMo

89.6Accuracy

Hindsight

56.8465.34573.8582.355Apr 23, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.04
89.6
2026.04
87.1
2026.04
75.8
2026.04
75.1
2026.04
74
2026.04
72.9
2026.04
68.4
2026.04
66.9
2026.04
58.1