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

Target

Benchmarks

Task NameDataset NameSOTA ResultTrend
Brain Tumor ClassificationTarget dataset
Macro F1 Score72.95
10
Task-free explorationTarget
SR (%)77.3
10
Clusteringtarget
ARI1
7
Autonomous Replicationtarget-1 citrusdrop
Non-refusal Rate48
4
Qualitative evaluation of conversational responsesTarget N=262
Constructive Guidance Score4.09
2
Showing 5 of 5 rows