| Benchmark | Model | Rank | Results |
|---|---|---|---|
| bias-detection-on-stereoset-1 | GPT-2 (small) | #1 | ICAT Score: 72.97 |
| bias-detection-on-stereoset-1 | XLNet (large) | #2 | ICAT Score: 72.03 |
| bias-detection-on-stereoset-1 | GPT-2 (medium) | #3 | ICAT Score: 71.73 |
| bias-detection-on-stereoset-1 | BERT (base) | #4 | ICAT Score: 71.21 |
| bias-detection-on-stereoset-1 | GPT-2 (large) | #5 | ICAT Score: 70.54 |
| bias-detection-on-stereoset-1 | BERT (large) | #6 | ICAT Score: 69.89 |
| bias-detection-on-stereoset-1 | RoBERTa (base) | #7 | ICAT Score: 67.50 |
| bias-detection-on-stereoset-1 | XLNet (base) | #9 | ICAT Score: 62.10 |