Our new X account is live! Follow @wizwand_team for updates
Search any
task
Feedback
Search any
task
SOTA Toxicity Classification benchmarks and papers with code | Wizwand
Our new X account is live! Follow @wizwand_team for updates
Home
/
Tasks
Toxicity Classification
Benchmarks
Dataset Name
SOTA Method
Dataset Name
SOTA Method
Metric
Trend
Results
Last Updated
CivilComments sensitive attribute: MUSLIM (test)
T5TT-4-ERM
Balanced Accuracy
59.9
57
4d ago
Average across WZ, DC, HX, OR
Ideal (Gold Label)
Harmonic F1
48.8
26
4d ago
OR
Ideal (Gold Labels)
Harmonic F1
49.7
26
4d ago
HX
Mistral-v0.3-FS
H.-F1
44.2
26
4d ago
DC
ToxiGAN
Harmonic Mean F1
31
26
4d ago
WZ
Back-Translate
Harmonic F1
73.4
26
4d ago
ToxCMM
ToxVidLM
F1 Score
94.35
24
4d ago
Toxigen
MAT-STEER
Accuracy
60.41
22
4d ago
Personification GPT-3 prompted (test)
V-REx
Loss
0.69
16
4d ago
RealToxicity Prompts GPT-3 prompted (test)
V-REx
Loss
0.61
16
4d ago
CivilComments (CC) (test)
gDRO
Worst-Group Accuracy
79.66
13
3d ago
Toxicity
AdvDemo + CW
Original Accuracy
90.4
4
4d ago
Toxicity Classification (test)
Template Attack
ASR
88.4
4
4d ago
English Civil Comments
PaLM 2
AUC-ROC
85.35
4
4d ago
Multilingual Jigsaw
PaLM 2
French Accuracy
87.94
4
4d ago
CivilComments
ERM
Average Accuracy
92.6
3
4d ago
ImplicitHate
Llama-3.2-3B-Instruct (SRD)
Accuracy
83.97
2
4d ago
Jigsaw-ML
No AT
AUC
98.4
2
4d ago
Jigsaw-BL
No AT
AUC
97.1
2
4d ago
Yorùbá (Aggregated Stratified K-Fold)
Hybrid TF-IDF + Logistic Regression with Lexicon- and Token-guided Rewriting
Accuracy
83
1
4d ago
isiXhosa (Aggregated Stratified K-Fold)
Hybrid TF-IDF + Logistic Regression with Lexicon- and Token-guided Rewriting
Accuracy
63
1
4d ago
Showing 21 of 21 rows
25 / page
50 / page
100 / page
1
Search any
task
Search any
task
Terms of Service
FAQs
