Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 52 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Image Classification | ImageNet ILSVRC 1000 images 2012 (val) | 180 | Feb 26, 2026 | ||
| Emotion Recognition in Conversation | MELD | 180 | May 20, 2026 | ||
| Human Pose Estimation | COCO 2017 (test-dev) | 180 | Feb 26, 2026 | ||
| Facial Landmark Detection | 300-W (Common) | 180 | Feb 26, 2026 | ||
| 3D Human Pose Estimation | Human3.6M (subjects 9 and 11) | 180 | Feb 26, 2026 | ||
| Object Classification | ModelNet40 (test) | 180 | Feb 26, 2026 | ||
| Person Re-identification | CUHK03 (Labeled) | 180 | Feb 26, 2026 | ||
| Language Modeling | WikiText-2 (val) | 179 | Jul 2, 2026 | ||
| Multimodal Evaluation | MME | 179 | Jun 23, 2026 | ||
| Medical Question Answering | MedQA | 179 | Jun 9, 2026 | ||
| Multimodal Sentiment Analysis | CMU-MOSI | 179 | Jul 9, 2026 | ||
| Image Classification | ImageNet-R (test) | 179 | Jun 25, 2026 | ||
| Node Clustering | Cora | 179 | Jun 12, 2026 | ||
| Graph Classification | D&D | 179 | Jul 3, 2026 | ||
| Graph Classification | BZR | 179 | Jun 11, 2026 | ||
| Concept Attribution | COCO | 178 | Feb 26, 2026 | ||
| Adversarial Attack | ImageNet | 178 | Feb 26, 2026 | ||
| Mortality prediction | MIMIC-IV | 178 | Jun 11, 2026 | ||
| Document Visual Question Answering | DocVQA (val) | 178 | Jul 7, 2026 | ||
| Instruction Following | UnNI | 178 | May 21, 2026 | ||
| Few-Shot Semantic Segmentation | COCO-20i | 178 | Apr 8, 2026 | ||
| Text-To-Video retrieval | MSRVTT (test) | 178 | Apr 28, 2026 | ||
| Image Generation | CIFAR-10 | 178 | Feb 26, 2026 | ||
| Few-shot classification | Mini-ImageNet | 178 | Mar 30, 2026 | ||
| Language Modeling | Penn Treebank (val) | 178 | Feb 26, 2026 |