LLM Generated Content Detection on GB Creative ChatGPT
96.255F1 ScoreTelescope Perplexity
Evaluation Results
| Method | Links | |
|---|---|---|
| Telescope PerplexityProtocol=Transferability (tuned on other datasets), Reference Models=Averaged2026.07 | 96.255 | |
| PerplexityProtocol=Transferability (tuned on other datasets), Reference Models=Averaged2026.07 | 89.799 | |
| DetectLLM LRRProtocol=Transferability (tuned on other datasets), Reference Models=Averaged2026.07 | 85.935 | |
| BinocularsProtocol=Transferability (tuned on other datasets), Reference Models=Averaged2026.07 | 85.858 | |
| Fast-DetectGPTProtocol=Transferability (tuned on other datasets), Reference Models=Averaged2026.07 | 72.314 |