Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1137 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Personalized Summarization | PerSum (test) | 25 | Feb 26, 2026 | ||
| Semantic Change Detection | ChangeSim | 25 | Feb 26, 2026 | ||
| Semantic Change Detection | TSUNAMI | 25 | May 21, 2026 | ||
| Semantic Change Detection | VL-CMU-CD | 25 | Feb 26, 2026 | ||
| Semantic Change Detection | ChangeVPR SF-XL (U) (test) | 25 | Feb 26, 2026 | ||
| Image Quality Evaluation | CelebA-HQ | 25 | Mar 26, 2026 | ||
| Long-form Egocentric Video Understanding | EgoSchema | 25 | Feb 26, 2026 | ||
| Domain Verification | DomainNet Mini | 25 | Feb 26, 2026 | ||
| Domain Verification | Office Home 65 | 25 | Feb 26, 2026 | ||
| Novel View Synthesis | RobustNeRF Crab | 25 | May 14, 2026 | ||
| Image-level Anomaly Detection | DTD | 25 | Feb 26, 2026 | ||
| Language Modeling | SlimPajama (test) | 25 | Jun 4, 2026 | ||
| Depth Estimation | NYUd | 25 | Apr 15, 2026 | ||
| Iterated Prisoner's Dilemma | IPD-Analytic (round robin) | 25 | Feb 26, 2026 | ||
| Image Classification | ImageNet-1K 1.0 (val) | 25 | Feb 26, 2026 | ||
| Oriented Object Detection | RSAR | 25 | Jun 5, 2026 | ||
| Face Verification | IJB-B (test) | 25 | Jul 1, 2026 | ||
| Image Classification | tieredImageNet | 25 | Feb 26, 2026 | ||
| SAR Classification | MSTAR SOCs (Standard operating conditions) 10-way | 25 | Feb 26, 2026 | ||
| Video Object Segmentation | 17 video datasets (EndoVis 2018, ESD, LVOSv2, LV-VIS, UVO, VOST, PUMaVOS, Virtual KITTI 2, VIPSeg, Wildfires, VISOR, FBMS, Ego-Exo4D, Cityscapes, Lindenthal Camera, HT1080WT Cells, and Drosophila Heart) zero-shot | 25 | Feb 26, 2026 | ||
| Affine-invariant depth estimation | KITTI | 25 | Jun 30, 2026 | ||
| Heart Rate Estimation | WildPPG | 25 | Feb 26, 2026 | ||
| Geometry Reconstruction | DTU (full) | 25 | Mar 9, 2026 | ||
| Multimodal Reasoning | LMMs-Eval Average of 12 benchmarks | 25 | Feb 26, 2026 | ||
| Object-level 3D Anomaly Detection | Real3D-AD | 25 | Mar 27, 2026 |