Long-form writing
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
86.7Overall Quality Score (S_bar)
25
Jun 4, 2026
0.798Score
23
Feb 26, 2026
95.42Score
18
Apr 21, 2026
83.17Score
18
Apr 21, 2026
88.27Score
18
Apr 21, 2026
9.5Score (D4 Lit/Arts)
14
Jun 4, 2026
21.5Sl Score
7
Feb 26, 2026
78.79Sl Score
7
Feb 26, 2026
92.1Sl Score
7
Feb 26, 2026