Distractor Generation
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
73.25Hardest Accuracy
18
May 20, 2026
22.39P@1
17
Feb 26, 2026
24.3Precision@1
15
Feb 26, 2026
21.05P@1
12
Apr 21, 2026
21.08P@1
12
Apr 21, 2026
24.24P@1
12
Apr 21, 2026
36.17P@1
12
Apr 21, 2026
25.5P@1
12
Apr 21, 2026
30.5P@1
12
Apr 21, 2026
3.25Plausibility
10
Apr 21, 2026
4.14Relevance
7
Apr 21, 2026
88.1Accuracy
7
Feb 26, 2026
0.1Invalid Ratio (Easy)
6
May 20, 2026
15.37F1@10
6
May 20, 2026
39.81BLEU-1
6
Feb 26, 2026
4.2Invalid Ratio
5
May 20, 2026
0Invalid Ratio
5
May 20, 2026
4.45Relevance
5
Feb 26, 2026
41.98F1@10
4
May 20, 2026
26.64F1@10
4
May 20, 2026
5Fluency
1
Feb 26, 2026
4.88Fluency
1
Feb 26, 2026
4.96Fluency
1
Feb 26, 2026
4.91Fluency
1
Feb 26, 2026
4.99Fluency
1
Feb 26, 2026