Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1321 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Spatiotemporal Video Super-Resolution | GoPro Center | 23 | Mar 6, 2026 | ||
| Audio Deepfake Detection | FakeOrReal (FOR) (test) | 23 | Mar 26, 2026 | ||
| Situated Question Answering | SQA3D (test) | 23 | Jul 9, 2026 | ||
| Image Classification Calibration | ImageNet | 23 | Jun 25, 2026 | ||
| Video Prediction | TaxiBJ (test) | 23 | Feb 26, 2026 | ||
| Multimodal Evaluation | Vision-Flan Multimodal Suite | 23 | Mar 4, 2026 | ||
| Medical Image Segmentation | COVID-Xray | 23 | Feb 26, 2026 | ||
| Anomaly Localization | VisA | 23 | Feb 26, 2026 | ||
| Science Question Answering | SQA IMG | 23 | Feb 26, 2026 | ||
| Deepfake Detection | DFD | 23 | Feb 26, 2026 | ||
| Sign Language Translation | BOBSL SENT (test) | 23 | Feb 27, 2026 | ||
| Free-form image cropping | GAICD | 23 | May 14, 2026 | ||
| Multivariate Time Series Forecasting | ETTh1 standard (test) | 23 | May 11, 2026 | ||
| Semantic Correspondence | SPair-71k | 23 | Feb 26, 2026 | ||
| Change Detection | S2Looking | 23 | Mar 23, 2026 | ||
| Real-world Single Image Super-Resolution | DRealSR (test) | 23 | May 25, 2026 | ||
| Multi-cancer Classification | CPTAC Aggregate | 23 | Feb 26, 2026 | ||
| Subtyping | CPTAC NSCLC | 23 | Feb 26, 2026 | ||
| Targeted Adversarial Attack | ImageNet (val) | 23 | Feb 26, 2026 | ||
| Crowd Counting | JHU-Crowd++ | 23 | Feb 26, 2026 | ||
| LiDAR Localization | QEOxford Average | 23 | Feb 26, 2026 | ||
| Conditional Image Generation | ImageNet 256x256 1.0 (train val) | 23 | Feb 26, 2026 | ||
| High Dynamic Range View Synthesis | HDR-NeRF Real Scenes LDR-NE (t2, t4) | 23 | Mar 31, 2026 | ||
| High Dynamic Range View Synthesis | HDR-NeRF Real Scenes LDR-OE (t1, t3, t5) | 23 | Mar 31, 2026 | ||
| Video Question Answering | VNBench | 23 | Apr 21, 2026 |