Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Commonsense Question Answering on CommonSenseQA n=425 (5%)
Loading...
61.22
Accuracy
MTO-AP
21.2632
31.6366
42.01
52.3834
Jun 23, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
MTO-AP
Evaluation Protocol=Fi...
2026.06
61.22
MTO-MCP
Evaluation Protocol=Fi...
2026.06
60.69
MTO-PreMAP
Evaluation Protocol=Pr...
2026.06
52.35
MVP-Tuning
2026.06
48.99
SAFE
2026.06
36.45
MTO-PreAP
Evaluation Protocol=Pr...
2026.06
33.41
QA-GNN
2026.06
32.95
GSC
2026.06
31.02
RoBERTa-large
Backbone=RoBERTa-large
2026.06
29.66
MHGRN
2026.06
29.01
MTO-MP
Evaluation Protocol=Fi...
2026.06
25.53
T5-large (baseline)
Evaluation Protocol=Fi...
2026.06
23.12
GreaseLM
2026.06
22.8
Feedback
Search any
task
Search any
task