Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 304 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| 3D Human Reconstruction | CAPE-NFP | 58 | Feb 26, 2026 | ||
| Long-term Human Motion Prediction | Human3.6M | 58 | Feb 26, 2026 | ||
| Image Compression | Kodak | 58 | May 25, 2026 | ||
| Automatic Speech Recognition | LRS3 (test) | 58 | Mar 19, 2026 | ||
| Image Classification | DomainNet | 58 | Feb 26, 2026 | ||
| Image Classification | ImageNet-R 1.0 (val) | 58 | Feb 27, 2026 | ||
| Speaker Identification | VoxCeleb1 | 58 | Feb 26, 2026 | ||
| Low-light Image Enhancement | DICM | 58 | Apr 8, 2026 | ||
| Low-light Image Enhancement | MEF | 58 | Apr 8, 2026 | ||
| Referring Image Segmentation | G-Ref Google split (val) | 58 | Feb 27, 2026 | ||
| Sentiment Classification | CR (test) | 58 | Feb 26, 2026 | ||
| Link Prediction | WN18 target | 58 | Feb 26, 2026 | ||
| 3D Single Object Tracking | KITTI (test) | 58 | Apr 16, 2026 | ||
| Natural Language Generation | E2E NLG Challenge | 58 | Feb 26, 2026 | ||
| Action Recognition | Toyota Smarthome CS | 58 | Jun 26, 2026 | ||
| Incremental Learning | ImageNet subset | 58 | Feb 26, 2026 | ||
| Face Recognition | CALFW | 58 | Jun 1, 2026 | ||
| Link Prediction | Wikidata5M (test) | 58 | Feb 26, 2026 | ||
| Image Harmonization | iHarmony4 HFlickr | 58 | Feb 26, 2026 | ||
| Oriented Object Detection | DOTA v1.5 (test) | 58 | May 6, 2026 | ||
| Text-to-Video Retrieval | ActivityNet Captions (val1) | 58 | Feb 27, 2026 | ||
| Few-shot Semantic Segmentation | FSS-1000 (test) | 58 | Feb 26, 2026 | ||
| Trajectory Prediction | Hotel ETH-UCY (test) | 58 | Apr 13, 2026 | ||
| Response Selection | Ubuntu (test) | 58 | Feb 26, 2026 | ||
| Named Entity Recognition | WikiAnn (test) | 58 | Feb 26, 2026 |