Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2056 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Sewer Pipe Defect Segmentation | Culvert sewer pipe defect dataset original | 17 | Feb 26, 2026 | ||
| Potato Disease Classification | Potato disease dataset | 17 | Feb 26, 2026 | ||
| Action Recognition | DailyDVS-200 (test) | 17 | Feb 26, 2026 | ||
| Histopathology Anomaly Detection | BRACS | 17 | Feb 26, 2026 | ||
| Histopathology Anomaly Detection | NCT-CRC | 17 | Feb 26, 2026 | ||
| Histopathology Anomaly Detection | SICAP v2 | 17 | Feb 26, 2026 | ||
| Histopathology Anomaly Detection | Camelyon16 HIS | 17 | Feb 26, 2026 | ||
| Video Compression | HEVC ClassB | 17 | Mar 10, 2026 | ||
| Zero-shot Classification | OxfordPets | 17 | Feb 27, 2026 | ||
| PCB Defect Analysis | UniPCB | 17 | Feb 26, 2026 | ||
| Novel View Synthesis | SeaThru-NeRF Curasao | 17 | Apr 7, 2026 | ||
| Image Restoration | TOLED | 17 | Feb 26, 2026 | ||
| Glaucoma TD Progression forecasting | Harvard-GDP (test) | 17 | Feb 26, 2026 | ||
| Class-Incremental Learning | Four within-domain datasets average (test) | 17 | Feb 26, 2026 | ||
| Document Understanding | AI2D (test) | 17 | Mar 12, 2026 | ||
| End-to-end Driving | NAVSIM v2 (test) | 17 | Jun 1, 2026 | ||
| Appearance Rendering | FAST-LIVO2 | 17 | Mar 18, 2026 | ||
| Inpainting (random) | ImageNet | 17 | Mar 4, 2026 | ||
| Inpainting (random) | FFHQ | 17 | May 28, 2026 | ||
| Image-Text Matching | SugarCrepe | 17 | Feb 26, 2026 | ||
| Sketch Reconstruction | DS2 | 17 | Mar 23, 2026 | ||
| Multi-modal Instruction Following | LLaVA-Wild | 17 | Mar 4, 2026 | ||
| 3D Object Detection | V2X-Real | 17 | Jun 29, 2026 | ||
| Medical Multi-task Visual Reasoning | MedAD-38K (test) | 17 | Feb 26, 2026 | ||
| Video Understanding | OV-Bench 1.0 (test) | 17 | Feb 26, 2026 |