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

Task 3

Benchmarks

Task NameDataset NameSOTA ResultTrend
Disease PredictionTask 3 Crohn's Disease (test)
AUROC100
10
Report writingTask 3 Cross-domain
LLM-as-Judge Score8.23
5
Report writingTask 3 Single-domain
LLM-as-Judge Score8.31
5
Topology OptimizationTask 3 Boundary Conditions
Minimum Compliance144.96
3
Showing 4 of 4 rows