LLM-generated content detection
Benchmarks
Dataset NameSOTA methodMetricTrendResultsLast Updated
5.04Stdev of F1 Score
12
Apr 30, 2026
4.68Std Dev of F1 Score
12
Apr 30, 2026
4.26Stdev(F1 Score)
12
Apr 30, 2026
4.87Std Dev of F1 Score
12
Apr 30, 2026
3.91Std Dev of F1 Score
12
Apr 30, 2026
95.76AUROC
11
May 8, 2026
0.975AUROC
11
May 8, 2026
0.872AUROC
11
May 8, 2026
0.946AUROC
11
May 8, 2026
0.817AUROC
11
May 8, 2026
0.982AUROC
11
May 8, 2026
0.955F1 Score
5
Jul 7, 2026
94.689F1 Score
5
Jul 7, 2026
88.829F1 Score
5
Jul 7, 2026
89.028F1 Score
5
Jul 7, 2026
79.833F1 Score
5
Jul 7, 2026
96.269F1 Score
5
Jul 7, 2026
93.922F1 Score
5
Jul 7, 2026
96.255F1 Score
5
Jul 7, 2026
93.763F1 Score
5
Jul 7, 2026
94.317F1 Score
5
Jul 7, 2026