PopQA
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
PopQA 10-shot
65.24Accuracy
3
PopQA
45.82Success Rate
2
PopQA
50.3PopQA Score
2
popQA Extreme (test)
—F1 Score
0
popQA Noisy (test)
—F1 Score
0
PopQA single-hop (test)
—Accuracy
0
Loading the SOTA2 catalog…