Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1899 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Semantic Segmentation | Pangaea Extended (50% train) | 18 | Feb 26, 2026 | ||
| Single-Image Super-resolution | SR-CACO-2 full image (test) | 18 | Feb 26, 2026 | ||
| Medical Image Restoration | ACDC | 18 | Jul 2, 2026 | ||
| Face Image Quality Assessment | SFIQA-Bench (test) | 18 | Feb 26, 2026 | ||
| Facial Image Quality Assessment | GFIQA-20K | 18 | Feb 26, 2026 | ||
| Spoken Term Detection | TIMIT OOV | 18 | Jun 26, 2026 | ||
| Spoken Term Detection | TIMIT (IV) | 18 | Jun 26, 2026 | ||
| Audio QA Correctness Assessment | MMAU and MMAR unseen question-based (test) | 18 | Feb 26, 2026 | ||
| Authentication Restoration | SafeSpeech Protected TTS Speech (test) | 18 | Feb 26, 2026 | ||
| Authentication Restoration | POP Protected TTS Speech (test) | 18 | Feb 26, 2026 | ||
| Authentication Restoration | GAN-ADV Protected TTS Speech (test) | 18 | Feb 26, 2026 | ||
| Authentication Restoration | Attack-VC Protected TTS Speech (test) | 18 | Feb 26, 2026 | ||
| Authentication Restoration | AntiFake Protected TTS Speech (test) | 18 | Feb 26, 2026 | ||
| Audio Classification | ESC50 | 18 | Jul 1, 2026 | ||
| Audio Classification | Average over 11 datasets | 18 | Jul 1, 2026 | ||
| Linear correlation between human MOS and automatic metrics | LibriTTS-P (test) | 18 | Feb 26, 2026 | ||
| Linear correlation between human MOS and automatic metrics | TextrolSpeech (test) | 18 | Feb 26, 2026 | ||
| Audio Generation | Speech clean (test) | 18 | Feb 26, 2026 | ||
| Audio Generation | Speech Noise SNR=-10 (test) | 18 | Feb 26, 2026 | ||
| Audio Generation | Sound Clean (test) | 18 | Feb 26, 2026 | ||
| Audio Generation | Sound Noise SNR=-10 (test) | 18 | Feb 26, 2026 | ||
| Audio Generation | Music clean (test) | 18 | Feb 26, 2026 | ||
| Audio Generation | Music Noise SNR=-10 (test) | 18 | Feb 26, 2026 | ||
| Automatic Speech Recognition | CommonVoice (test) | 18 | Jun 2, 2026 | ||
| Audio Quality Assessment | LibriSpeech | 18 | Feb 26, 2026 |