Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1073 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Nonlinear Deblur | FFHQ | 26 | May 21, 2026 | ||
| Medical Image Segmentation | BraTS 2019 (20% labeled data) | 26 | May 26, 2026 | ||
| Mathematical Multimodal Reasoning | MM-Math | 26 | Mar 4, 2026 | ||
| Domain Adaptation | VisDA-C (test) | 26 | Feb 26, 2026 | ||
| Embodied Question Answering | OpenEQA | 26 | Jun 11, 2026 | ||
| Video Understanding | LVBench (test) | 26 | Jun 12, 2026 | ||
| Novel View Synthesis | D-RE10K-iPhone full-image fidelity (test) | 26 | Feb 26, 2026 | ||
| Novel View Synthesis | D-RE10K static regions only (test) | 26 | Feb 26, 2026 | ||
| Video Question Answering | MLVU 1.0 (test) | 26 | May 22, 2026 | ||
| Multi-Label Class-Incremental Learning | PASCAL VOC (B4-C2) | 26 | Mar 9, 2026 | ||
| Image Classification | Web-Bird (test) | 26 | Feb 26, 2026 | ||
| Image Classification | Web-Aircraft (test) | 26 | Feb 26, 2026 | ||
| Pulse Rate Estimation | PURE to UBFC-rPPG (test) | 26 | May 25, 2026 | ||
| Monocular Depth Estimation | HAMMER | 26 | Apr 24, 2026 | ||
| Few-Shot Class-Incremental Learning | CUB200 | 26 | Feb 26, 2026 | ||
| Few-Shot Class-Incremental Learning | CIFAR100 multi-class 5-shot | 26 | Feb 26, 2026 | ||
| Medical image classification | INbreast | 26 | Jun 23, 2026 | ||
| Face Restoration | CelebA synthetic (test) | 26 | Apr 14, 2026 | ||
| Image Restoration | POLED | 26 | Mar 17, 2026 | ||
| Classification | Oxford Pets zero-shot | 26 | Mar 31, 2026 | ||
| Multimodal Understanding and Reasoning | MME | 26 | Feb 26, 2026 | ||
| Out-of-Distribution Detection | FMNIST | 26 | May 26, 2026 | ||
| Image Dehazing | RESIDE | 26 | May 14, 2026 | ||
| STEM & Puzzle | MMMU (val) | 26 | Jul 2, 2026 | ||
| Multimodal Understanding | MMMU zero-shot | 26 | Feb 26, 2026 |