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

ShopTrajQA

Benchmarks

Task NameDataset NameSOTA ResultTrend
Tool-use ReasoningShopTrajQA 32k context
Accuracy62.6
14
Tool-use ReasoningShopTrajQA 64k context
Accuracy60.1
13
Showing 2 of 2 rows