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

Reveal

Benchmarks

Task NameDataset NameSOTA ResultTrend
Vulnerability DetectionReveal (test)
Precision48.3
42
Binary Fact-checkingREVEAL
Macro-F193.7
14
Vulnerability DetectionREVEAL Chromium Linux Debian Kernel (test)
Precision0.483
12
Fact-CheckingReveal
Balanced Accuracy89.8
7
Showing 4 of 4 rows