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

AA-LCR

Benchmarks

Task NameDataset NameSOTA ResultTrend
Long Context ReasoningAA-LCR
Score53.5
26
Long-context ReasoningAA-LCR
Accuracy81
12
General Task (Agentic Coding)AA-LCR
Score74
6
Long Context ReasoningAA-LCR
Accuracy66.9
5
Long Context UnderstandingAA-LCR
Accuracy68
5
Long Context & Context LearningAA-LCR
Pass@158.5
4
Showing 6 of 6 rows