LLM-Generated Text Detection on GB Creative Claude (test)
0.966AUROCTelescope
Evaluation results
| Method | Links | |
|---|---|---|
| TelescopeAggregation=Average AUROC across 12 reference models2026.07 | 0.966 | |
| PerplexityAggregation=Average AUROC across 12 reference models2026.07 | 0.893 | |
| DetectLLMAggregation=Average AUROC across 12 reference models2026.07 | 0.8745 | |
| BinocularsAggregation=Average AUROC across 12 reference models2026.07 | 0.8293 | |
| Fast-DetectGPTAggregation=Average AUROC across 12 reference models2026.07 | 0.6028 |