Text Quality Assessment
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
4.17Average Rank
20
May 26, 2026
0.842PLCC
16
Mar 10, 2026
12.188Perplexity (PPL)
11
Jul 1, 2026
0.942PLCC
6
Mar 10, 2026
0.75Preference Better
4
Feb 26, 2026
0.67GPT-4 Preference Ratio (Better)
4
Feb 26, 2026
3.55Fluency Score
2
Mar 4, 2026
3.47Fluency
2
Mar 4, 2026