Table 8 Accuracy of the detection tools (binary inclusive approach)
Tool | 01-Hum | 02-MT | 03-AI | 04-AI | 05-ManEd | 06-Para | Total | Accuracy | Rank |
|---|---|---|---|---|---|---|---|---|---|
Check For AI | 9 | 7 | 9 | 8 | 4 | 3 | 40 | 74% | 4 |
Compilatio | 9 | 9 | 9 | 8 | 6 | 2 | 43 | 80% | 2 |
Content at Scale | 9 | 9 | 0 | 0 | 0 | 0 | 18 | 33% | 14 |
Crossplag | 9 | 6 | 9 | 7 | 5 | 2 | 38 | 70% | 9 |
DetectGPT | 9 | 8 | 9 | 8 | 4 | 2 | 40 | 74% | 4 |
Go Winston | 8 | 8 | 9 | 8 | 5 | 2 | 40 | 74% | 4 |
GPT Zero | 6 | 3 | 8 | 9 | 8 | 8 | 42 | 78% | 3 |
GPT-2 Output Detector Demo | 9 | 7 | 9 | 8 | 5 | 2 | 40 | 74% | 4 |
OpenAI Text Classifier | 9 | 9 | 5 | 8 | 5 | 2 | 38 | 70% | 9 |
PlagiarismCheck | 9 | 8 | 5 | 6 | 3 | 3 | 34 | 63% | 12 |
TurnItIn | 9 | 9 | 9 | 9 | 5 | 3 | 44 | 81% | 1 |
Writeful GPT Detector | 9 | 8 | 8 | 6 | 3 | 1 | 35 | 65% | 11 |
Writer | 9 | 7 | 5 | 6 | 4 | 2 | 33 | 61% | 13 |
Zero GPT | 9 | 8 | 7 | 8 | 4 | 4 | 40 | 74% | 4 |