Binary text classification on TURINGBENCH (Turing Test, FAIR_wmt20)

Metric: F1 score (higher is better)

LeaderboardDataset
Loading chart...
#ModelF1 scoreExtra DataPaperDateCode
1GigaCheck (Mistral-7B)0.9966NoGigaCheck: Detecting LLM-generated Content2024-10-31-
2RoBERTa0.4531NoTURINGBENCH: A Benchmark Environment for Turing ...2021-09-27Code