Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 74 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Novel View Synthesis | LLFF | 144 | Jul 7, 2026 | ||
| Face Alignment | WFLW (test) | 144 | Feb 27, 2026 | ||
| Privacy Mechanism Evaluation | Approximate Differential Privacy | 143 | May 28, 2026 | ||
| Long-context understanding | LongBench | 143 | May 19, 2026 | ||
| Image Classification | CIFAR10 | 143 | May 22, 2026 | ||
| dynamic link prediction | LastFM (transductive) | 143 | Jul 7, 2026 | ||
| Chart Understanding and Reasoning | ChartQA | 143 | Jul 7, 2026 | ||
| Multi-task Language Understanding | MMLU | 143 | Jun 23, 2026 | ||
| Multi-Hop QA | HotPotQA | 143 | May 25, 2026 | ||
| Person Re-Identification | Market1501 | 143 | Jun 2, 2026 | ||
| Mathematical Reasoning | MultiArith | 143 | Mar 6, 2026 | ||
| Multimodal Reasoning | MMStar | 143 | Mar 31, 2026 | ||
| Referring Video Object Segmentation | Ref-YouTube-VOS | 143 | Jun 26, 2026 | ||
| Multimodal Understanding | SEED-Bench Image | 143 | May 29, 2026 | ||
| Time Series Imputation | ETTm2 | 143 | Jul 9, 2026 | ||
| Out-of-Distribution Detection | ImageNet-1k ID iNaturalist OOD | 143 | Jun 17, 2026 | ||
| Novel View Synthesis | Mip-NeRF 360 | 143 | Mar 24, 2026 | ||
| Novel View Synthesis | LLFF 6-view | 143 | Jul 2, 2026 | ||
| Text-to-image generation | MS-COCO 2014 (val) | 143 | May 19, 2026 | ||
| Semantic Segmentation | PASCAL VOC classic 2012 (val) | 143 | Feb 26, 2026 | ||
| Skeleton-based Action Recognition | NTU-RGB+D 120 (Cross-Subject) | 143 | Feb 26, 2026 | ||
| Skin Lesion Segmentation | ISIC 2018 (test) | 143 | May 12, 2026 | ||
| Monocular Depth Estimation | Make3D (test) | 143 | Jul 2, 2026 | ||
| Question Answering | NQ (test) | 143 | Jun 30, 2026 | ||
| Polyp Segmentation | Kvasir | 143 | Apr 14, 2026 |