LLM-Generated Text Detection on HC3 (test)
0.9947AUROCPerplexity
Evaluation results
| Method | Links | |
|---|---|---|
| PerplexityAggregation=Average AUROC across 12 reference models2026.07 | 0.9947 | |
| BinocularsAggregation=Average AUROC across 12 reference models2026.07 | 0.9944 | |
| TelescopeAggregation=Average AUROC across 12 reference models2026.07 | 0.9916 | |
| DetectLLMAggregation=Average AUROC across 12 reference models2026.07 | 0.9844 | |
| Fast-DetectGPTAggregation=Average AUROC across 12 reference models2026.07 | 0.9558 |