Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2485 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Audio Generation | MMAU Sound (Clean) | 15 | Feb 26, 2026 | ||
| Audio Generation | MMAU Music (Noise) | 15 | Feb 26, 2026 | ||
| Audio Generation | MMAU Music (Clean) | 15 | Feb 26, 2026 | ||
| Acoustic Target Recognition | ShipsEar (test) | 15 | Apr 20, 2026 | ||
| Preference Evaluation | SpeechJudge | 15 | Feb 26, 2026 | ||
| Preference Evaluation | SpeechEval | 15 | Feb 26, 2026 | ||
| Preference Evaluation | URGENT SQA 24 | 15 | Feb 26, 2026 | ||
| Preference Evaluation | TMHINT-QI | 15 | Feb 26, 2026 | ||
| Preference Evaluation | SOMOS | 15 | Feb 26, 2026 | ||
| Preference Evaluation | URGENT25-SQA | 15 | Feb 26, 2026 | ||
| Preference Evaluation | CHiME UDASE 7 (test) | 15 | Feb 26, 2026 | ||
| Preference Evaluation | NISQA-FOR | 15 | Feb 26, 2026 | ||
| Preference Evaluation | NISQA-P501 | 15 | Feb 26, 2026 | ||
| Speech enhancement | WSJ0 UNI | 15 | Feb 26, 2026 | ||
| Mixed-emotion Text-to-Speech | IEMOCAP (out-of-distribution) | 15 | Feb 26, 2026 | ||
| Mixed-emotion Text-to-Speech | CREMA-D (in-distribution) | 15 | Feb 26, 2026 | ||
| Music Source Restoration | MSR Challenge 2025 (test) | 15 | Mar 5, 2026 | ||
| Audio Classification | AudioMarathon 1.0 (test) | 15 | Feb 26, 2026 | ||
| Speaker Information Modeling | AudioMarathon 1.0 (test) | 15 | Feb 26, 2026 | ||
| Speech Content Extraction | AudioMarathon 1.0 (test) | 15 | Feb 26, 2026 | ||
| Spoken Dialogue | URO-Bench Chinese Basic Track | 15 | Feb 26, 2026 | ||
| Motion Planning | NAVSIM v2 (test) | 15 | Feb 26, 2026 | ||
| Point-goal navigation | InternScenes Home (test) | 15 | Mar 11, 2026 | ||
| Floorplan Localization | Structured3D (full) | 15 | Feb 26, 2026 | ||
| Multi-stage Robotic Manipulation | Kitchen (test) | 15 | May 14, 2026 |