Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1949 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Mathematical Reasoning | TabMWP | 18 | Apr 14, 2026 | ||
| Mathematical Problem Solving | Gaokao MathCloze | 18 | Feb 26, 2026 | ||
| Unconditional image generation | LSUN Church | 18 | Feb 26, 2026 | ||
| Text Classification | Average All Datasets | 18 | Feb 26, 2026 | ||
| Text Classification | MASSIVE (test) | 18 | Feb 26, 2026 | ||
| Region Captioning | Visual Genome | 18 | Feb 26, 2026 | ||
| Novel view synthesis | D-NeRF Standup | 18 | May 12, 2026 | ||
| Novel view synthesis | D-NeRF Mutant | 18 | May 12, 2026 | ||
| Novel view synthesis | D-NeRF BouncingBalls | 18 | May 12, 2026 | ||
| Novel view synthesis | D-NeRF Jumpingjacks | 18 | May 12, 2026 | ||
| Novel view synthesis | D-NeRF Hook | 18 | May 12, 2026 | ||
| Super-resolution | CelebA-HQ 1K | 18 | Feb 26, 2026 | ||
| Cross-Domain Few-Shot Classification | CUB (test) | 18 | Feb 26, 2026 | ||
| Novel view rendering | ACID (medium overlap) | 18 | Jul 1, 2026 | ||
| Novel view rendering | ACID small overlap | 18 | Jul 1, 2026 | ||
| 3D Human Mesh Recovery | 3DPW OC (test) | 18 | May 12, 2026 | ||
| Multimodal Evaluation | MMBench EN (test) | 18 | May 26, 2026 | ||
| Object Detection | INRIA Person dataset (test) | 18 | Feb 26, 2026 | ||
| Tumor and Lymph Node Segmentation | New Dataset 2 | 18 | Feb 26, 2026 | ||
| Tumor and Lymph Node Segmentation | New Dataset 1 | 18 | Feb 26, 2026 | ||
| Tumor and Lymph Node Segmentation | HECKTOR 2022 (train) | 18 | Feb 26, 2026 | ||
| Video Matting | V-HIM60 Medium | 18 | Jun 26, 2026 | ||
| Motion Deblurring | RealBlur JPEG (test) | 18 | Feb 26, 2026 | ||
| Image Classification | Circuit Diagram (test) | 18 | Feb 26, 2026 | ||
| No-Reference Image Quality Assessment | PIPAL (test) | 18 | Feb 26, 2026 |