Question Formation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
100Full Accuracy
20
Jun 23, 2026
100Full Accuracy (Test)
18
Jun 23, 2026
99Partial Accuracy
12
Jun 23, 2026
8.563Full Accuracy (Log Ratio)
5
Jun 23, 2026
22.2Full Accuracy
5
Jun 23, 2026