Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

SIMMC

Benchmarks

Task NameDataset NameSOTA ResultTrend
Coreference ResolutionSIMMC 2.1
Precision59.98
22
Multimodal ReasoningSIMMC 2.0
Score79.86
13
Preference Reasoning (Recommendation)SIMMC 2.1 (test)
R@138.75
13
Response GenerationSIMMC 2.1 (test)
BLEU-133.77
13
Multi-modal Response GenerationSIMMC 2.0
BLEU34.1
5
Multi-modal Dialog State TrackingSIMMC 2.0
Slot F188.3
5
Showing 6 of 6 rows