List your company

ResearchFormerly WizWand

Contextual Robustness Question Answering

Benchmarks

DatasetSOTA methodMetricTrendResultsLast updated

ConflictQA Unknown queries

99.28Accuracy (Short Context)

22

Feb 26, 2026

ConflictQA (Known queries)

82.49Accuracy (Contradictory Short)

22

Feb 26, 2026