Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 427 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Single Image Reflection Removal | Objects 200 images (test) | 47 | Jul 1, 2026 | ||
| Video Temporal Grounding | ActivityNet-Captions | 47 | Jun 30, 2026 | ||
| Few-shot Image Classification | Average 11 datasets (test) | 47 | Apr 10, 2026 | ||
| Image Classification | ImageNet | 47 | Feb 26, 2026 | ||
| Code Generation | MultiPL-E | 47 | Jun 11, 2026 | ||
| 3D Reconstruction | DTU | 47 | Mar 10, 2026 | ||
| Image Classification | Oxford Flowers | 47 | Jul 8, 2026 | ||
| Question Answering | QA | 47 | May 4, 2026 | ||
| Semantic Segmentation | ISPRS Vaihingen (test) | 47 | May 19, 2026 | ||
| Image Reconstruction | ImageNet 50k (val) | 47 | Apr 24, 2026 | ||
| Image Classification | CIFAR-100 IID | 47 | Apr 27, 2026 | ||
| Visual Question Answering | RealWorldQA (test) | 47 | May 19, 2026 | ||
| Image Deepfake Detection | FFIW | 47 | May 12, 2026 | ||
| Registration | ShapeNet In-Context | 47 | Apr 6, 2026 | ||
| Time Series Imputation | Weather (test) | 47 | Jul 9, 2026 | ||
| Time Series Imputation | ETTh2 (test) | 47 | Jul 9, 2026 | ||
| Offline Reinforcement Learning | D4RL MuJoCo Hopper medium standard | 47 | Jun 11, 2026 | ||
| Underwater Image Enhancement | EUVP (test) | 47 | May 12, 2026 | ||
| Open-Vocabulary Semantic Segmentation | PC-459 | 47 | Apr 15, 2026 | ||
| Class-unconditional image generation | ImageNet 256x256 | 47 | Jul 7, 2026 | ||
| Tabular Data Synthesis | steel | 47 | Feb 26, 2026 | ||
| Tabular Data Synthesis | biodeg | 47 | Feb 26, 2026 | ||
| Optic Cup / Disc Segmentation | Fundus Domain 1 | 47 | Mar 27, 2026 | ||
| 6D Object Pose Estimation | BOP 7 core datasets: LM-O, T-LESS, TUD-L, IC-BIN, ITODD, HB, YCB-V 82 (test) | 47 | Feb 26, 2026 | ||
| Grammatical Error Correction | BEA 2019 (test) | 47 | Jun 16, 2026 |