Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

LAILA

Benchmarks

Task NameDataset NameSOTA ResultTrend
Automated Essay ScoringLAILA (cross-prompt)
Relevance Score55.7
5
Automated Essay ScoringLAILA
P1 Score0.537
3
Trait-level Essay ScoringLAILA (test)
Relevance0.411
3
Showing 3 of 3 rows