Automated essay scoring
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
0.836Prompt 1 QWK
51
Feb 26, 2026
99.02Accuracy
22
Mar 9, 2026
0.72Quadratic Weighted Kappa
14
Apr 23, 2026
0.84QWK
13
Feb 26, 2026
0.73Score P1
11
May 26, 2026
0.744Score P1
10
Jun 19, 2026
0.94Pearson Correlation (ρ)
10
Jun 2, 2026
0.734Score P1
10
Feb 26, 2026
49.51QWK
7
May 19, 2026
53.59QWK
7
May 19, 2026
45.64QWK
7
May 19, 2026
75.97Prompt 1 Score
7
Feb 26, 2026
2.08RMSE
6
May 26, 2026
0.632RMSE
6
May 26, 2026
0.635QWK (P1)
6
Feb 26, 2026
0.726QWK
5
May 26, 2026
0.743QWK
5
May 26, 2026
55.7Relevance Score
5
Mar 4, 2026
0.603QWK (Cohesion)
4
May 26, 2026
83.6Score (P1)
4
Feb 26, 2026
79.6Pearson's r
4
Feb 26, 2026
0.537P1 Score
3
Apr 21, 2026
0.659Score P1
3
Apr 21, 2026
0.792QWK
3
Feb 26, 2026
0.779QWK
2
Apr 23, 2026