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

MMT-Bench

Benchmarks

Task NameDataset NameSOTA ResultTrend
Multimodal ReasoningMMT-Bench
Accuracy57.88
23
Multi-image UnderstandingMMT-Bench (val)
Score71.8
23
Multimodal UnderstandingMMT-Bench
Accuracy59.2
19
Multimodal EvaluationMMT-Bench
Accuracy62.65
13
Multimodal tasksMMT-Bench 1.0 (test)
Overall63.4
13
Showing 5 of 5 rows