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

IQ

Benchmarks

Task NameDataset NameSOTA ResultTrend
Vision-centric reasoningIQ (test)
Accuracy30
4
Sequence generationIQ dataset
Cross Entropy Loss2.2335
3
Utility EvaluationIQ Dataset
Metric-
0
Showing 3 of 3 rows