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

Long-horizon Memory Question Answering on ATM-Bench subset431

69.61EM

Graph-NoReader

65.990866.930467.8768.8096Apr 10, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.04
69.613,672.11
2026.04
68.212,962.01
2026.04
66.13751.09