Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1416 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Aspect Extraction and Sentiment Classification (AESC) | 14lap (test) | 22 | Feb 26, 2026 | ||
| Domain Adaptation | DomainNet target | 22 | Feb 26, 2026 | ||
| Semantic Segmentation | Pascal-VOC 2012 (Overlap) | 22 | Feb 26, 2026 | ||
| Point Cloud Registration | KITTI odometry | 22 | Feb 26, 2026 | ||
| Node Classification | MS Academic | 22 | Feb 26, 2026 | ||
| Image Classification | ImageNet ILSVRC 10% labeled examples 2012 | 22 | Feb 26, 2026 | ||
| Image Classification | CIFAR10 100 clients (test) | 22 | Feb 26, 2026 | ||
| Audio recognition | VGG-Sound (test) | 22 | Feb 26, 2026 | ||
| Vision-Language Navigation | R4R (val seen) | 22 | Feb 26, 2026 | ||
| top-n recommendation | Netflix Prize Dataset | 22 | Feb 26, 2026 | ||
| top-n recommendation | MovieLens 20M | 22 | Feb 26, 2026 | ||
| Multi-person 3D pose estimation | Campus frames 350-470, 650-750 (test) | 22 | Apr 21, 2026 | ||
| Video Captioning | TVC (val) | 22 | Feb 27, 2026 | ||
| Image Classification | SVHN 1.0 (test) | 22 | Feb 26, 2026 | ||
| Orientation Estimation | KITTI Car class official (test) | 22 | Feb 27, 2026 | ||
| Fine-grained Entity Typing | FIGER (test) | 22 | Feb 26, 2026 | ||
| Paraphrase Identification | PAWS-X (test) | 22 | Apr 28, 2026 | ||
| Hateful Meme Detection | Hateful Memes (val) | 22 | Feb 26, 2026 | ||
| Node Classification | Citeseer (60 20 20 random split) | 22 | Feb 26, 2026 | ||
| Neural Architecture Search | NAS-Bench-101 1.0 (test) | 22 | Feb 26, 2026 | ||
| Passage retrieval | SQuAD (test) | 22 | Feb 26, 2026 | ||
| Scene Graph Generation | VG150 | 22 | Apr 27, 2026 | ||
| RGB saliency detection | DUTS | 22 | Feb 26, 2026 | ||
| Speaker verification | VoxCeleb 1 (verification) | 22 | Feb 26, 2026 | ||
| Depth Estimation | Sun3D (test) | 22 | Feb 26, 2026 |