Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 788 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Explanation Plausibility | MDACE bigger (test) | 32 | Feb 27, 2026 | ||
| Image Classification | CIFAR10 instance-dependent noise (test) | 32 | Feb 26, 2026 | ||
| Aspect-Sentiment Triplet Extraction | 16res (test) | 32 | Apr 13, 2026 | ||
| Grasp Detection | GraspNet-1Billion (RealSense) | 32 | Feb 26, 2026 | ||
| Multivariate Long-term Time Series Forecasting | Traffic | 32 | Feb 26, 2026 | ||
| Multivariate Long-term Time Series Forecasting | Electricity | 32 | Feb 26, 2026 | ||
| Human-Object Interaction Detection | V-COCO | 32 | Feb 26, 2026 | ||
| HOI Detection | HICO-DET (test) | 32 | Feb 27, 2026 | ||
| Surface Normal Estimation | Hi4D | 32 | Mar 30, 2026 | ||
| Visual Question Answering | MMHalSnowball HalluConv 1.0 | 32 | Feb 26, 2026 | ||
| Visual Question Answering | MMHalSnowball CleanConv 1.0 | 32 | Feb 26, 2026 | ||
| Action Recognition | HMDB-51 Few-shot | 32 | Feb 26, 2026 | ||
| Visual Question Answering | GQA balanced (test-dev) | 32 | Feb 26, 2026 | ||
| 3D Object Detection | Waymo Open Dataset (WOD) (test) | 32 | May 25, 2026 | ||
| Scientific Natural Language Inference | SciNLI 1.0 (test) | 32 | Feb 26, 2026 | ||
| Univariate Time Series Forecasting | ETTh2 | 32 | Jun 8, 2026 | ||
| AI-Generated Text Detection | Cross-genre (test) | 32 | Feb 26, 2026 | ||
| Molecule graph property prediction | ogbg-molbbbp (test) | 32 | Jun 30, 2026 | ||
| Knowledge Base Question Answering | GraphQ (test) | 32 | May 29, 2026 | ||
| Machine Translation | ZHUANGBENCH (test) | 32 | Feb 27, 2026 | ||
| Creative Translation | CommonMT | 32 | Feb 26, 2026 | ||
| Image Classification | CIFAR-100 Class-IL (5T) | 32 | Feb 26, 2026 | ||
| Surgical Instrument Segmentation | EndoVis 2018 (test) | 32 | Feb 26, 2026 | ||
| Video Summarization | SumMe | 32 | Feb 26, 2026 | ||
| Black-box Attack | CelebA-HQ | 32 | Jun 17, 2026 |