LLM-Generated Text Detection on GB Creative Deepseek V3 (test)
0.9957AUROCBinoculars
Evaluation results
| Method | Links | |
|---|---|---|
| BinocularsAggregation=Average AUROC across 12 reference models2026.07 | 0.9957 | |
| PerplexityAggregation=Average AUROC across 12 reference models2026.07 | 0.9885 | |
| TelescopeAggregation=Average AUROC across 12 reference models2026.07 | 0.982 | |
| DetectLLMAggregation=Average AUROC across 12 reference models2026.07 | 0.9639 | |
| Fast-DetectGPTAggregation=Average AUROC across 12 reference models2026.07 | 0.9044 |