Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2216 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Semantic Segmentation | Potsdam&Vaihingen Cross Spectral Band | 16 | Mar 17, 2026 | ||
| Semantic Segmentation | LoveDA Cross-Style | 16 | Mar 17, 2026 | ||
| Semantic Segmentation | FLAIR Cross-Regional | 16 | Mar 17, 2026 | ||
| Semantic Segmentation | Five-Billion-Pixels (Cross-Regional) | 16 | Mar 17, 2026 | ||
| Semantic Segmentation | Five-Billion-Pixels Cross-sensor | 16 | Mar 17, 2026 | ||
| Video Anomaly Detection | UCF-Crime 6 (clip-level) | 16 | Mar 17, 2026 | ||
| Natural Language Understanding | GLUE | 16 | May 11, 2026 | ||
| Image Editing | GEdit | 16 | Jun 12, 2026 | ||
| Deepfake Detection | DFD v1 (test) | 16 | May 12, 2026 | ||
| Breast Cancer Subtype Prediction | BRACS → BACH | 16 | Mar 17, 2026 | ||
| Novel View Synthesis | LLFF 2 input views | 16 | Mar 17, 2026 | ||
| Depth Estimation | LLFF 4 input views (test) | 16 | Mar 17, 2026 | ||
| Topological Anomaly Detection | Topological Anomaly Detection Sample-level | 16 | Mar 16, 2026 | ||
| Topological Anomaly Detection | Topological Anomaly Detection | 16 | Mar 16, 2026 | ||
| Private Inference Efficiency | WAN4 Environment | 16 | Mar 16, 2026 | ||
| Private Inference Efficiency | WAN3 Environment | 16 | Mar 16, 2026 | ||
| Private Inference Efficiency | WAN1 Environment | 16 | Mar 16, 2026 | ||
| Goal-reaching navigation | Simulation Goal Sequence 150° (Zigzag) | 16 | Mar 16, 2026 | ||
| Goal-reaching navigation | Simulation 120° (Zigzag) Goal Sequence | 16 | Mar 16, 2026 | ||
| Goal-reaching navigation | Simulation Goal Sequence 90° (CCW) | 16 | Mar 16, 2026 | ||
| Goal-reaching navigation | Simulation 60° (CW) Goal Sequence | 16 | Mar 16, 2026 | ||
| Statistical Randomness Testing | NIST SP 800-22 | 16 | Mar 16, 2026 | ||
| Re-identification | HOSS-ReID (All-to-All) | 16 | Mar 16, 2026 | ||
| Text-to-Image Generation | GenEval 22 | 16 | Mar 16, 2026 | ||
| Molecular activity ranking | MoleculeNet HIV (test) | 16 | Mar 16, 2026 |