Table 9 Accuracy of the detection tools (semi-binary approach)
Tool | 01-Hum | 02-MT | 03-AI | 04-AI | 05-ManEd | 06-Para | Total | Accuracy | Rank |
|---|---|---|---|---|---|---|---|---|---|
Check For AI | 9 | 3.5 | 9 | 8 | 4 | 2.5 | 36 | 67% | 6 |
Compilatio | 8.5 | 9 | 8.5 | 8 | 5.5 | 2 | 41.5 | 77% | 2 |
Content at Scale | 9 | 9 | 0 | 0 | 0 | 0 | 18 | 33% | 14 |
Crossplag | 9 | 6 | 9 | 7 | 4.5 | 2 | 37.5 | 69% | 5 |
DetectGPT | 9 | 6.5 | 5.5 | 8 | 2 | 1.5 | 32.5 | 60% | 10 |
Go Winston | 7.5 | 7.5 | 9 | 8 | 4.5 | 1.5 | 38 | 70% | 4 |
GPT Zero | 6 | 3 | 7.5 | 8 | 5.5 | 5.5 | 35.5 | 66% | 8 |
GPT-2 Output Detector Demo | 9 | 7 | 9 | 8 | 5 | 1.5 | 39.5 | 73% | 3 |
OpenAI Text Classifier | 9 | 8.5 | 3.5 | 7.5 | 3.5 | 1.5 | 33.5 | 62% | 9 |
PlagiarismCheck | 8 | 6.5 | 4 | 4.5 | 2 | 2.5 | 27.5 | 51% | 13 |
Turnitin | 9 | 9 | 8.5 | 9 | 4.5 | 2.5 | 42.5 | 79% | 1 |
Writeful GPT Detector | 9 | 7.5 | 5 | 4.5 | 2.5 | 0.5 | 29 | 54% | 12 |
Writer | 9 | 7 | 4.5 | 5 | 3 | 1.5 | 30 | 56% | 11 |
Zero GPT | 9 | 6.5 | 7 | 8 | 3 | 2.5 | 36 | 67% | 6 |
Average | 95% | 77% | 71% | 74% | 39% | 22% |