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

Key-Value Recall

Benchmarks

Task NameDataset NameSOTA ResultTrend
General Reasoning and CodingKey-Value Recall Non-Factoid
GSM8K Accuracy64.1
6
Factoid Knowledge RecallKey-Value Recall Factoid
ID Score10.6
6
Key-Value RecallKey-Value Recall
LAMA Recall47.5
2
Showing 3 of 3 rows