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

VitaminC

Benchmarks

Task NameDataset NameSOTA ResultTrend
Complex reasoningVitaminC (test)
Macro-F178.4
37
Fact VerificationVitaminC
Accuracy (%)54
12
global fact consistency verificationVitaminC
Precision0.984
10
Fact VerificationVitaminC
Accuracy92.62
8
Complex reasoningVitaminC (val)
Macro F1 Score69.99
4
Showing 5 of 5 rows