Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Decoding on Common Numeracy Benchmarks
Loading...
0.3
RMSE ([0, 10^2])
NTL-WAS
-0.892
7.154
15.2
23.246
Mar 5, 2026
RMSE ([0, 10^2])
RMSE ([0, 10^3])
RMSE ([0, 10^4])
RMSE ([0, 10^5])
RMSE ([0, 10^6])
Updated 1mo ago
Evaluation Results
Method
Method
Links
RMSE ([0, 10^2])
RMSE ([0, 10^3])
RMSE ([0, 10^4])
RMSE ([0, 10^5])
RMSE ([0, 10^6])
NTL-WAS
2026.03
0.3
0.49
2.75
18.4
45
CONE
2026.03
0.42
0.73
2.71
4.89
9.85
DICE
2026.03
0.45
0.83
3.02
5.42
11.2
BioBERT
2026.03
3.28
29.7
434
4.1
40.5
Random vectors
2026.03
30.1
295.88
2,888.62
28
280
Feedback
Search any
task
Search any
task