Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

S1

Benchmarks

Task NameDataset NameSOTA ResultTrend
Membership Inference AttackS1 Distillation Gemini-2.0-flash
AUROC0.852
7
Membership Inference AttackS1.1 Distillation Deepseek-R1
AUROC98.4
7
Nuclear SegmentationS1 (full)
AJI+77.3
6
Point-level consensus correctness predictionS1
AUPRC99.7
4
Showing 4 of 4 rows