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

MC2

Benchmarks

Task NameDataset NameSOTA ResultTrend
Modality Preference SteeringMC2 Text Preference 1.0 (test)
Sport Score83.2
6
Modality Preference SteeringMC2 Vision Preference 1.0 (test)
Sport78.8
6
Vision-Text ArbitrationMC2
Adversarial Accuracy83.5
4
Entropy EstimationMC2
Exp(Estimated Entropy)1.938
3
Minimal Entropy Strategy SynthesisMC2
EntAns0.662
1
Showing 5 of 5 rows