Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Downstream Task Evaluation on 10 Downstream Tasks
Loading...
52.79
Average Accuracy
MeSH
38.8748
42.4874
46.1
49.7126
Oct 9, 2025
Average Accuracy
Accuracy Change
Updated 1mo ago
Evaluation Results
Method
Method
Links
Average Accuracy
Accuracy Change
MeSH
Model Size=Pythia-1.4B...
2025.10
52.79
0.86
MeSH
Model Size=Pythia-1.4B...
2025.10
50.56
1.06
Vanilla
Model Size=Pythia-1.4B...
2025.10
49.5
-
MeSH
Model Size=Pythia-410M...
2025.10
46.04
0.73
MeSH
Model Size=Pythia-410M...
2025.10
44.12
0.25
Vanilla
Model Size=Pythia-410M...
2025.10
43.87
-
MeSH
Model Size=160M, Schem...
2025.10
40.6
0.06
Vanilla
Model Size=160M, Schem...
2025.10
39.88
-
MeSH
Model Size=160M, Schem...
2025.10
39.41
-0.47
Feedback
Search any
task
Search any
task