TriState-Bench
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
TriState-Bench Sagr
94.25EM Score
76
TriState-Bench Sres
94.25EM
76
TriState-Bench Scor
92.5Exact Match (EM)
76
TriState-Bench
64.92EM
24
TriState-Bench Agreement Sagr gold context, prior correct
93.75Exact Match (EM)
24
TriState-Bench Resistance corrupted context, prior correct (Sres)
33.25EM
24
TriState-Bench Correction gold context, prior incorrect (Scor)
91.25Exact Match (EM)
24