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

MM-AlignBench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Human Preference AlignmentMM-AlignBench 1.0 (test)
Win Rate84.9
18
Multi-modal preference alignmentMM-AlignBench
Winning Rate62.3
6
Showing 2 of 2 rows