SimpleQA
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
SimpleQA
87.7Accuracy
4
SimpleQA (test)
77.1Pass@1 Accuracy
4
simpleQA
16.82Score
3
SimpleQA
3.07Accuracy
3
SimpleQA (test)
4.05SimpleQA Score
3
SimpleQA
4Accuracy
2
SimpleQA (held-out questions)
2Computational Cost (Generations Factor)
1
SimpleQA (200 random samples)
0.981Alignment Score
1