Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 970 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Long-context video understanding | LongVideoBench (test) | 28 | Feb 26, 2026 | ||
| Image Classification | CIFAR-10C | 28 | May 12, 2026 | ||
| Binary Change Detection | SYSU, LEVIR-CD+, and WHU-CD (test) | 28 | Feb 26, 2026 | ||
| Binary Change Detection | LEVIR-CD+ | 28 | Feb 26, 2026 | ||
| Binary Change Detection | SYSU (test) | 28 | Feb 26, 2026 | ||
| Heart Rate Estimation | DaLiA | 28 | Jun 8, 2026 | ||
| Locomotion | D4RL Hopper-medium-expert | 28 | May 19, 2026 | ||
| Mathematical Reasoning | TheoremQA (test) | 28 | Feb 26, 2026 | ||
| Image-Text Matching | Sugar-Crepe | 28 | Jun 19, 2026 | ||
| Image Classification | CIFAR-10 LT (IF=200) | 28 | May 12, 2026 | ||
| Online Continual Learning | CIFAR10 (test) | 28 | Feb 26, 2026 | ||
| Online Continual Learning | CIFAR10 | 28 | Feb 26, 2026 | ||
| Action Retrieval | NTU-60 (x-view) | 28 | Mar 12, 2026 | ||
| Action Retrieval | NTU-60 (x-sub) | 28 | Mar 12, 2026 | ||
| Image Classification | ImageNet-1K (val) | 28 | Feb 26, 2026 | ||
| Class-Incremental Learning | CIFAR | 28 | Feb 27, 2026 | ||
| Multi-agent trajectory simulation | Waymo Open Sim Agents Challenge (WOSAC) 2024 (test) | 28 | Jun 19, 2026 | ||
| Multimodal Benchmarking | MMBench | 28 | Jun 9, 2026 | ||
| Cross-View Geo-Localization | VIGOR-Graph 1.0 (test) | 28 | Feb 26, 2026 | ||
| Cross-View Geo-Localization | SpaGBOL 1.0 (test) | 28 | Feb 26, 2026 | ||
| Image Classification | Aircraft | 28 | Jun 5, 2026 | ||
| Object Detection | Radiate | 28 | Feb 26, 2026 | ||
| Traffic Signal Control | New York (DNY) | 28 | Feb 26, 2026 | ||
| Time Series Forecasting | M3 (test) | 28 | Apr 1, 2026 | ||
| Graph Continual Learning | CoraFull (test) | 28 | Feb 26, 2026 |