Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Numerical Reasoning on NUPA (aggregated)
Loading...
72.4
Exact Match
NumValue-RNN
62.936
65.393
67.85
70.307
Jan 14, 2026
Exact Match
Digit Match
d-Length
Updated 4d ago
Evaluation Results
Method
Method
Links
Exact Match
Digit Match
d-Length
NumValue-RNN
2026.01
72.4
86.2
0.09
NumValue-MLP
2026.01
72
86.4
0.06
Standard Transformer
2026.01
68.7
83.9
0.068
Numerologic
2026.01
63.3
78.1
1.039
Feedback
Search any
task
Search any
task