LLM-Generated Text Detection on ESL GPT4o Mini (test)
0.9998AUROCTelescope
Evaluation Results
| Method | Links | |
|---|---|---|
| TelescopeAggregation=Average AUROC across 12 reference models2026.07 | 0.9998 | |
| PerplexityAggregation=Average AUROC across 12 reference models2026.07 | 0.8252 | |
| BinocularsAggregation=Average AUROC across 12 reference models2026.07 | 0.7964 | |
| DetectLLMAggregation=Average AUROC across 12 reference models2026.07 | 0.6905 | |
| Fast-DetectGPTAggregation=Average AUROC across 12 reference models2026.07 | 0.606 |