Multilingual Question Answering
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
81.9Accuracy
65
Mar 12, 2026
48.86F1 Score (1-shot macro)
28
Apr 2, 2026
80Ar Score
20
Apr 7, 2026
32.9Accuracy
12
Jun 2, 2026
77.4Accuracy (All)
10
Jun 1, 2026
44.75Accuracy
10
Feb 26, 2026
57.82Composite Score (ALL-AVG)
6
Jul 7, 2026
2.8AR Score
6
Apr 29, 2026
48.71F1 Score
4
Mar 31, 2026
26Overall Score
4
Mar 19, 2026
21.6Overall Score
4
Mar 19, 2026
18LC
3
Jul 7, 2026
9LC Score
3
Jul 7, 2026
89.29Normalized Performance
3
Mar 4, 2026
60.28Normalized Performance
3
Mar 4, 2026
63.64Accuracy
1
Mar 18, 2026