List your company

ResearchFormerly WizWand

Supporting Fact Prediction

Benchmarks

DatasetSOTA methodMetricTrendResultsLast updated

HotpotQA full wiki (dev)

86.5F1 Score

19

Feb 26, 2026

HotpotQA distractor (dev)

Gated Memory Flow

89F1 Score

13

Feb 26, 2026