Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Summarization on NEWTS
Loading...
73.44
Correlation Score (Corr)
BERTScore
-115.84
-66.7
-17.56
31.58
May 26, 2026
Correlation Score (Corr)
Incorrect Score (Incorr)
N Delta (NΔ)
Updated 7d ago
Evaluation Results
Method
Method
Links
Correlation Score (Corr)
Incorrect Score (Incorr)
N Delta (NΔ)
BERTScore
2026.05
73.44
66.14
7.3
MATCHA
rescaled to [0, 1]=true
2026.05
44.64
16.53
14.06
SimCSE
rescaled to [0, 1]=true
2026.05
39.45
11.53
13.96
EmbSim
rescaled to [0, 1]=true
2026.05
30.89
5.69
12.61
R1-F1
2026.05
19.18
8.7
10.48
RL-F1
2026.05
12.74
6.8
5.94
METEOR
2026.05
10.41
3.74
6.67
R2-F1
2026.05
2.91
0.39
2.52
MAUVE
2026.05
1.64
0.75
0.89
BLEURT
rescaled to [0, 1]=true
2026.05
-108.56
-135.69
13.57
Feedback
Search any
task
Search any
task
