Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2089 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Binary Classification | TABFACT complex (test) | 17 | Feb 26, 2026 | ||
| Binary Classification | TABFACT simple (test) | 17 | Feb 26, 2026 | ||
| Multiple Choice Question Answering | OBQA (dev) | 17 | Feb 26, 2026 | ||
| Speech Synthesis | LibriTTS (test) | 17 | May 28, 2026 | ||
| AMR Parsing | BioAMR (test) | 17 | Feb 26, 2026 | ||
| Video Virtual Try-on | VVT (test) | 17 | Feb 26, 2026 | ||
| Few-shot action classification | UCF101 | 17 | Feb 26, 2026 | ||
| Keypoint matching | HPatches All variations | 17 | Feb 26, 2026 | ||
| Flat Named Entity Recognition | OntoNotes 5.0 (test) | 17 | Feb 26, 2026 | ||
| Question Answering | LogiQA | 17 | Mar 16, 2026 | ||
| Person Re-identification | Market-SCT | 17 | Feb 26, 2026 | ||
| Action Recognition | UCF | 17 | Feb 27, 2026 | ||
| Action Recognition | HMDB | 17 | Feb 27, 2026 | ||
| Semantic Role Prediction | VidSitu (test) | 17 | Feb 26, 2026 | ||
| Visual Place Recognition | MSLS | 17 | Jul 2, 2026 | ||
| Temporal Action Detection | ActivityNet | 17 | Feb 26, 2026 | ||
| Audio Question Answering | MUSIC-AVQA (test) | 17 | Feb 26, 2026 | ||
| Digit Recognition | USPS to SVHN (test) | 17 | Feb 26, 2026 | ||
| Digit Recognition | SVHN to USPS (test) | 17 | Feb 26, 2026 | ||
| 3D Hand Shape and Color Reconstruction | DeepHandMesh (test) | 17 | Feb 26, 2026 | ||
| Machine Translation | en-fr (test) | 17 | Feb 26, 2026 | ||
| Word Alignment | English-Hindi en-hi (test) | 17 | Feb 26, 2026 | ||
| Point Cloud Registration | ModelNet40 | 17 | Jul 1, 2026 | ||
| Temporal Grounding | Charades-CG (Novel-Composition) | 17 | Jul 2, 2026 | ||
| Visual Grounding | ReferCOCOg UMD (val) | 17 | Feb 26, 2026 |