LLM-Generated Text Detection on GB News ChatGPT (test)
99.05AUROCDetectLLM
Evaluation results
| Method | Links | |
|---|---|---|
| DetectLLMAggregation=Average AUROC across 12 reference models2026.07 | 99.05 | |
| PerplexityAggregation=Average AUROC across 12 reference models2026.07 | 98.817 | |
| BinocularsAggregation=Average AUROC across 12 reference models2026.07 | 98.773 | |
| Fast-DetectGPTAggregation=Average AUROC across 12 reference models2026.07 | 91.94 | |
| TelescopeAggregation=Average AUROC across 12 reference models2026.07 | 90.48 |