| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| Resume screening dataset ground truth GPT-5.1 | Qwen3-8B (AutoScreen-FW) | Accuracy86.82 | 6 | 1mo ago | |
| Resume Screening GPT-o3 labels | Accuracy73.87 | 6 | 1mo ago | ||
| Resume quality judgment GPT-5.2 as ground truth | Accuracy69.17 | 6 | 1mo ago |