CRSArena-Eval
Benchmarks
TaskDatasetSOTA resultTrendResults
CRSArena-Eval KG
0.766Pearson Correlation (r)
44
CRSArena-Eval RD
0.712Pearson Correlation (r)
44
CRSArena-Eval KG (test)
0.543Pearson r (Turn-level Rel.)
6
CRSArena-Eval RD (test)
0.549Pearson r (Turn-level Rel)
6