Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1628 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Medical Segmentation | KiTS | 20 | Jun 1, 2026 | ||
| Novel View Synthesis | Deblur-NeRF Real-Scene 1.0 (test) | 20 | Feb 26, 2026 | ||
| World modeling | WorldPrediction-WM | 20 | Feb 26, 2026 | ||
| Privacy Attribute Recognition | VPHMDB | 20 | Mar 30, 2026 | ||
| Image Classification | Flowers102 | 20 | Apr 7, 2026 | ||
| Video Question Answering | LongVideoBench KFS-Bench (full set) | 20 | Feb 26, 2026 | ||
| Video Question Answering | VideoMME KFS-Bench full set | 20 | Feb 26, 2026 | ||
| Image Immunization | StableDiffusion 1.4 (test) | 20 | Feb 26, 2026 | ||
| Video Temporal Grounding | QVHighlights TimeLens | 20 | May 22, 2026 | ||
| Human Preference Alignment | PickScore | 20 | May 11, 2026 | ||
| Face Template Inversion Attack | Age-DB | 20 | Feb 26, 2026 | ||
| Face Template Inversion Attack | CelebA-HQ | 20 | Feb 26, 2026 | ||
| Optical Character Recognition | OCR | 20 | Apr 21, 2026 | ||
| Object Detection | MRTMD native 4K (test) | 20 | Feb 26, 2026 | ||
| Fine-grained classification | Fine-grained classification datasets Average of Caltech101, Pets, Cars, Flower102, Aircraft, DTD, EuroSAT, UCF101 (test) | 20 | May 20, 2026 | ||
| Task planning | MomaGraph-Bench Overall 1.0 | 20 | Feb 26, 2026 | ||
| Task planning | MomaGraph-Bench Tier 4 1.0 | 20 | Feb 26, 2026 | ||
| Task planning | MomaGraph-Bench 1.0 (Tier 3) | 20 | Feb 26, 2026 | ||
| Task planning | MomaGraph-Bench Tier 2 1.0 | 20 | Feb 26, 2026 | ||
| Task planning | MomaGraph-Bench 1.0 (Tier 1) | 20 | Feb 26, 2026 | ||
| Monocular Depth Estimation | KITTI | 20 | Feb 26, 2026 | ||
| Multi-image reasoning | OmniContext | 20 | Feb 26, 2026 | ||
| Novel View Synthesis | ACID zero-shot | 20 | Mar 27, 2026 | ||
| Drone-view geo-localization | SUES-200 Drone→Satellite 300m altitude 1.0 (test) | 20 | Feb 26, 2026 | ||
| Drone-view geo-localization | SUES-200 Drone→Satellite, 200m altitude 1.0 (test) | 20 | Feb 26, 2026 |