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

ATM-Bench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Long-term Memory Question AnsweringATM-Bench 1.0 (test)
QS77.8
15
Memory Question AnsweringATM-Bench Hard
QS Score74.7
7
Memory Question AnsweringATM-Bench
QS Score86
7
Long-horizon Memory Question AnsweringATM-Bench subset431
EM69.61
3
Showing 4 of 4 rows