Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 141 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Enhancing Tumour Segmentation | BraTS 2018 (test) | 95 | Jun 9, 2026 | ||
| Referring Segmentation | refCOCO (testA) | 95 | Jul 8, 2026 | ||
| Multi-hop QA | MuSiQue | 95 | May 25, 2026 | ||
| Instruction Following | AlpacaEval 2.0 (test) | 95 | May 19, 2026 | ||
| Image Classification | Average 11 datasets | 95 | Jun 4, 2026 | ||
| Video-to-Audio Generation | VGGSound (test) | 95 | Jun 15, 2026 | ||
| Compositional Reasoning | SugarCrepe | 95 | Jul 7, 2026 | ||
| Pansharpening | WorldView-3 full-resolution original (test) | 95 | Apr 13, 2026 | ||
| Capacitated Vehicle Routing Problem | CVRP N=100 | 95 | Jun 19, 2026 | ||
| Referring Expression Segmentation | RefCOCOg (val-u) | 95 | Jun 4, 2026 | ||
| 3D Object Classification | Objaverse-LVIS (test) | 95 | Feb 27, 2026 | ||
| OOD Detection | iNaturalist | 95 | May 11, 2026 | ||
| Question Answering | QuALITY (test) | 95 | Jun 26, 2026 | ||
| Node Classification | Cornell (60%/20%/20% random) | 95 | Mar 11, 2026 | ||
| Image Retrieval | Revisited Oxford (ROxf) + R1M (Medium) | 95 | Feb 26, 2026 | ||
| Link Prediction | ogbl-wikikg2 (test) | 95 | Feb 26, 2026 | ||
| Visual Question Answering | ChartQA (test) | 95 | Jun 9, 2026 | ||
| Untargeted Adversarial Attack | CIFAR-10 (test) | 95 | Mar 31, 2026 | ||
| Node Classification | Pokec | 95 | Jun 2, 2026 | ||
| Traffic Forecasting | PeMSD7 (test) | 95 | Mar 4, 2026 | ||
| Graph property prediction | ToxCast | 95 | Apr 14, 2026 | ||
| Graph property prediction | MUV | 95 | Apr 14, 2026 | ||
| Image Classification | DomainNet | 95 | May 12, 2026 | ||
| Stereo Matching | ETH3D | 95 | Jul 1, 2026 | ||
| Referring Image Segmentation | G-Ref (val) | 95 | Feb 27, 2026 |