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

RecipeQA

Benchmarks

Task NameDataset NameSOTA ResultTrend
Multimodal SequencingRecipeQA Golden (test)
Accuracy92.12
12
Procedural ReasoningRecipeQA
BertScore46.6
10
Procedural Multimodal Machine ComprehensionRecipeQA (test)
Cloze77.6
10
Textual ClozeRecipeQA (test)
Accuracy73.6
9
Showing 4 of 4 rows