GB Essay
Benchmarks
Task NameDataset NameSOTA ResultTrendResults
GB Essay Deepseek V3 (test)
99.881AUROC
5
GB Essay Claude (test)
95.988AUROC
5
GB Essay GPT4o (test)
99.365AUROC
5
GB Essay ChatGPT (test)
99.81AUROC
5
GB Essay Deepseek V3
94.689F1 Score
5
GB Essay Claude
88.829F1 Score
5
GB Essay GPT4o
93.922F1 Score
5
GB Essay ChatGPT
94.317F1 Score
5