Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1018 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Anomaly Detection | Wilt | 27 | Feb 26, 2026 | ||
| Out-of-Distribution Detection | SVHN (In) CelebA (Out) (test) | 27 | May 22, 2026 | ||
| Short-term Forecasting | PEMS07 (test) | 27 | Feb 26, 2026 | ||
| Knee Injury Detection | Knee Injury Dataset ITBS (test) | 27 | Feb 26, 2026 | ||
| Knee Injury Detection | Knee Injury Dataset PFPS (test) | 27 | Feb 26, 2026 | ||
| Knee Injury Detection | Knee Injury Dataset PFPS+ITBS (test) | 27 | Feb 26, 2026 | ||
| LLM Decoding | Llama 70B (H100 GPU Cluster) 3.1 | 27 | Feb 26, 2026 | ||
| Rating Prediction | AmazonBook | 27 | May 11, 2026 | ||
| Question Answering | TriviaQA (test) | 27 | Mar 25, 2026 | ||
| Image Captioning | MSCOCO | 27 | Feb 26, 2026 | ||
| Long Video Understanding | VideoMME Long split, 30-60 min | 27 | Apr 21, 2026 | ||
| Point Cloud Completion | ShapeNet-21 (Unseen) | 27 | May 20, 2026 | ||
| Image Classification | ImageNet Mini | 27 | Feb 26, 2026 | ||
| Referring Expression Segmentation | RRSIS-D | 27 | Apr 10, 2026 | ||
| Visible-Infrared Person Re-Identification | SYSU-MM01 Indoor Search v1 | 27 | Feb 26, 2026 | ||
| Visual Grounding | ScreenSpot-Pro 1.0 (test) | 27 | Feb 26, 2026 | ||
| Hyperspectral Image Super-Resolution | PaviaC (test) | 27 | Feb 26, 2026 | ||
| Text-to-Image Generation | GenEval | 27 | Mar 13, 2026 | ||
| Respiratory Rate Estimation | MAHNOB | 27 | Feb 26, 2026 | ||
| Respiratory Rate Estimation | OmuSense (test) | 27 | Feb 26, 2026 | ||
| AI-generated video detection | GenVideo Morph Studio | 27 | Jun 11, 2026 | ||
| Video Generation | WorldScore (test) | 27 | Jun 9, 2026 | ||
| Object Detection | M3FD | 27 | Jul 1, 2026 | ||
| Multi-view Crowd Counting | CityStreet (test) | 27 | Feb 26, 2026 | ||
| Multi-view crowd counting | PETS 2009 (test) | 27 | Feb 26, 2026 |