Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Language Understanding on MMLU-ProX
Loading...
27.7
Accuracy
Naive Fine-tuning
26.972
27.161
27.35
27.539
Apr 22, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Naive Fine-tuning
Backbone=Phi-4-Mini-In...
2026.04
27.7
COMPASS-ECDA
Backbone=Phi-4-Mini-In...
2026.04
27.6
Full Retraining
Backbone=Phi-4-Mini-In...
2026.04
27.5
EWC
Backbone=Phi-4-Mini-In...
2026.04
27.2
Random Rehearsal
Backbone=Phi-4-Mini-In...
2026.04
27
Feedback
Search any
task
Search any
task