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

Multimodal Safety Evaluation on SafeBench

3.26FS ASR

Claude-3.5-Sonnet

-0.192823.113646.4269.7264Nov 30, 2024
Updated 4d ago

Evaluation Results

MethodLinks
2024.11
3.261.341.6953.4238.118.14
2024.11
6.193.9196.4297.3996.4296.74
2024.11
13.687.8296.4295.7796.4294.14
2024.11
89.5853.7592.5196.7492.1891.86