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

UniICL-Bench

Benchmarks

Task NameDataset NameSOTA ResultTrend
UnderstandingUniICL-Bench
Perception Score80.9
33
GenerationUniICL-Bench
Perception86.5
15
In-Context Learning Stability AnalysisUniICL-Bench (test)
Random Replace Error (Und.)2.1
4
Showing 3 of 3 rows