Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1607 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Semantic Segmentation | Five-Billion-Pixels (FBP) (val) | 20 | Mar 4, 2026 | ||
| Image Classification | ForestNet (val) | 20 | Mar 4, 2026 | ||
| Image Classification | FireRisk (val) | 20 | Mar 4, 2026 | ||
| Semantic Segmentation | DFC 2023 | 20 | Mar 4, 2026 | ||
| Visual-Inertial Odometry | Castle Around | 20 | Mar 4, 2026 | ||
| Single Image Super-Resolution | Average Set5, Set14, BSDS100, Urban100, Manga109 x4 (test) | 20 | Apr 24, 2026 | ||
| Seizure Forecasting | MSSM Intracranial EEG Dataset | 20 | Mar 4, 2026 | ||
| Inverse Dynamics Identification | Multi-Robot Aggregate Real and Simulated | 20 | Mar 4, 2026 | ||
| Inverse Dynamics Identification | Talos (test) | 20 | Mar 4, 2026 | ||
| Inverse Dynamics Identification | Talos (train) | 20 | Mar 4, 2026 | ||
| Inverse Dynamics Identification | Spot with Arm (test) | 20 | Mar 4, 2026 | ||
| Inverse Dynamics Identification | Spot with Arm (train) | 20 | Mar 4, 2026 | ||
| Inverse Dynamics Identification | Spot (test) | 20 | Mar 4, 2026 | ||
| Inverse Dynamics Identification | Spot (train) | 20 | Mar 4, 2026 | ||
| Inverse Dynamics Identification | HyQReal2 (test) | 20 | Mar 4, 2026 | ||
| Inverse Dynamics Identification | HyQReal2 (train) | 20 | Mar 4, 2026 | ||
| Medical Reasoning | MedXpertQA | 20 | Jul 3, 2026 | ||
| Posterior Estimation | Air-traffic 15 countries | 20 | Mar 4, 2026 | ||
| 3D affordance grounding | PIAD (Unseen) | 20 | Jul 7, 2026 | ||
| 3D affordance grounding | PIAD (Seen) | 20 | Jul 7, 2026 | ||
| Motor Imagery | PhysioNet-MI | 20 | Apr 21, 2026 | ||
| Controllable Robustness Curve Prediction | SW networks | 20 | Mar 4, 2026 | ||
| Controllable Robustness Curve Prediction | QSN networks | 20 | Mar 4, 2026 | ||
| Controllable Robustness Curve Prediction | SF networks | 20 | Mar 4, 2026 | ||
| Controllable Robustness Curve Prediction | ER networks | 20 | Mar 4, 2026 |