Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Toxicity Detection on CivilComments (test)
Loading...
78.8
WGA
JTT
49.888
57.394
64.9
72.406
Feb 6, 2026
Feb 17, 2026
Feb 28, 2026
Mar 11, 2026
Mar 22, 2026
Apr 2, 2026
Apr 14, 2026
WGA
Average Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
WGA
Average Accuracy
JTT
2026.04
78.8
87.8
DFR
2026.04
77.8
87.8
SG
2026.04
74.8
88.2
ERM
2026.04
73.7
88
NFL
2026.04
71.7
83.2
LEIA
Group Info (Train/Val)...
2026.02
71.6
91.4
DPE
Group Info (Train/Val)...
2026.02
69.9
82.2
CRT
Group Info (Train/Val)...
2026.02
67.8
82.7
LISA
Group Info (Train/Val)...
2026.02
65.8
84.6
ReWeightCRT
Group Info (Train/Val)...
2026.02
64.7
82.4
DFR
Group Info (Train/Val)...
2026.02
64.4
80.7
ERM
Group Info (Train/Val)...
2026.02
63.2
85.4
CVaRDRO
Group Info (Train/Val)...
2026.02
62.9
81.6
JTT
Group Info (Train/Val)...
2026.02
51
79
Feedback
Search any
task
Search any
task