List your company

ResearchFormerly WizWand

Pronoun Resolution

Benchmarks

DatasetSOTA methodMetricTrendResultsLast updated

UnifiedQA-T5-11B

89.4Accuracy

64

Jun 18, 2026

57.7Accuracy

19

May 12, 2026

0.931Accuracy

14

Feb 26, 2026

85.6Accuracy

8

Feb 26, 2026

WinoGrande (test)

58.68Single Accuracy

7

Feb 26, 2026