Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Stack Manipulation on Formal-language benchmark lengths 41-500 (test)
Loading...
100
Accuracy
SRNN
54.24
66.12
78
89.88
May 16, 2026
Accuracy
Updated 16d ago
Evaluation Results
Method
Method
Links
Accuracy
SRNN
Architecture=Stack-RNN
2026.05
100
TRNN
Architecture=Tape-RNN
2026.05
100
LSTM
2026.05
59.1
Transformer
Architecture=encoder-only
2026.05
57.5
PR-LSTM
2026.05
56.3
RNN
2026.05
56
Feedback
Search any
task
Search any
task
