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

Demonstration Selection on Demo-ICL-Bench

76Overall Accuracy

Human

12.0428.64545.2561.855Feb 9, 2026
Updated 4d ago

Evaluation Results

MethodLinks
2026.02
7688
26-
2026.02
24.5-
2026.02
2458
2026.02
21.554.5
2026.02
20.544.5
2026.02
18.552
2026.02
1846
2026.02
1854
2026.02
1848
2026.02
17.548
2026.02
16.544
2026.02
1643
2026.02
14.538