Table 13 False positive (false accusation) ratio
Tool | 01-Hum | 02-MT | Total | FPR |
|---|---|---|---|---|
Check For AI | 0 | 1 | 1 | 5.6% |
Compilatio | 0 | 0 | 0 | 0.0% |
Content at Scale | 0 | 0 | 0 | 0.0% |
Crossplag | 0 | 3 | 3 | 16.7% |
DetectGPT | 0 | 0 | 0 | 0.0% |
Go Winston | 0 | 0 | 0 | 0.0% |
GPT Zero | 3 | 6 | 9 | 50.0% |
GPT-2 Output Detector Demo | 0 | 2 | 2 | 11.1% |
OpenAI Text Classifier | 0 | 0 | 0 | 0.0% |
PlagiarismCheck | 0 | 0 | 0 | 0.0% |
Turnitin | 0 | 0 | 0 | 0.0% |
Writeful GPT Detector | 0 | 1 | 1 | 5.6% |
Writer | 0 | 1 | 1 | 5.6% |
Zero GPT | 0 | 0 | 0 | 0.0% |
Average | 2.4% | 11.1% |