Table 1 Performance metrics for various purported AI detectors compared to human evaluators. Here TP is True Positive, FP False Positive, TN True Negative and FN False Negative
Detector | TP | FP | TN | FN | Accuracy | Precision |
|---|---|---|---|---|---|---|
GPTZero | 33 | 2 | 26 | 7 | 86.76% | 0.94 |
Quillbot | 37 | 0 | 28 | 3 | 95.59% | 1.0 |
ZeroGPT | 16 | 0 | 28 | 24 | 64.71% | 1.0 |
Human | 30 | 4 | 24 | 10 | 79.41% | 0.88 |