LLM-Generated Text Detection on GB Essay Claude (test)
95.988AUROCDetectLLM
Evaluation Results
| Method | Links | |
|---|---|---|
| DetectLLMAggregation=Average AUROC across 12 reference models2026.07 | 95.988 | |
| PerplexityAggregation=Average AUROC across 12 reference models2026.07 | 94.31 | |
| TelescopeAggregation=Average AUROC across 12 reference models2026.07 | 94.223 | |
| BinocularsAggregation=Average AUROC across 12 reference models2026.07 | 77.288 | |
| Fast-DetectGPTAggregation=Average AUROC across 12 reference models2026.07 | 61.633 |