List your company
ResearchFormerly WizWand

Question Answering

Benchmarks

DatasetSOTA methodMetricTrendResultsLast updated
2Wiki Normal (test)
—
—F1 Score
Question Answering on 2Wiki Normal (test) performance trend
0
Feb 26, 2026
popQA Extreme (test)
—
—F1 Score
Question Answering on popQA Extreme (test) performance trend
0
Feb 26, 2026
popQA Noisy (test)
—
—F1 Score
Question Answering on popQA Noisy (test) performance trend
0
Feb 26, 2026
TrivialQA Noisy (test)
—
—F1 Score
Question Answering on TrivialQA Noisy (test) performance trend
0
Feb 26, 2026
NQ Extreme (test)
—
—F1
Question Answering on NQ Extreme (test) performance trend
0
Feb 26, 2026
NQ Normal (test)
—
—F1 Score
Question Answering on NQ Normal (test) performance trend
0
Feb 26, 2026