SAFE Audio Challenge Task 2: leaderboard
SAFE Audio Challenge Task 2 evaluates generated audio detection systems with additional augmentation-source robustness metrics.
Metric: Balanced Accuracy (%). Source: huggingface.co. 11 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | baseline-2 | 85.97 | |
| 2 | baseline-1 | 84 | |
| 3 | ISPL | 82.23 | |
| 4 | ISSF | 81.9 | |
| 5 | Anon_Peking | 80.96 | |
| 6 | JAIST-HIS | 73.39 | |
| 7 | viper-purdue | 71.39 | |
| 8 | csun22 | 56.18 | |
| 9 | DMF | 54.23 | |
| 10 | safe-test | 51.4 |
Interactive version: theaggregate.ai/benchmark?slug=safe-audio-challenge-task-2 · How It Works · Data refreshed daily, snapshot 2026-10-20.