DCI Evaluation Suite
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
DCI Evaluation Suite Routine
8.96Quality Score
5
DCI Evaluation Suite Arch.
9.19Quality Score
5
DCI Evaluation Suite Policy
8.97Quality Score
5
DCI Evaluation Suite Disagree
8.87Quality Score
5
DCI Evaluation Suite Risk
8.85Quality Score
5
DCI Evaluation Suite Late-Evid.
9.6Quality Score
5
DCI Evaluation Suite Hidden-Prof
9.56Quality Score
5