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

Tier III

Benchmarks

Task NameDataset NameSOTA ResultTrend
Physical law recoveryTier III 10% noise, 50% hidden
Exact Recovery Rate61.2
5
Ambiguity detectionTier III 10% noise
Ambiguity Detection Accuracy91.3
1
Showing 2 of 2 rows