Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Even Pairs on Formal-language benchmark lengths 41-500 (test)
Loading...
100
Accuracy (%)
RNN
96.256
97.228
98.2
99.172
May 16, 2026
Accuracy (%)
Updated 16d ago
Evaluation Results
Method
Method
Links
Accuracy (%)
RNN
2026.05
100
SRNN
Architecture=Stack-RNN
2026.05
100
TRNN
Architecture=Tape-RNN
2026.05
100
LSTM
2026.05
100
PR-LSTM
2026.05
100
Transformer
Architecture=encoder-only
2026.05
96.4
Feedback
Search any
task
Search any
task
