Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 887 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Text Classification | DBpedia (val) | 30 | Feb 26, 2026 | ||
| Text Classification | SST (val) | 30 | Feb 26, 2026 | ||
| Text Classification | TREC (val) | 30 | Feb 26, 2026 | ||
| Text Classification | AGNews (val) | 30 | Feb 26, 2026 | ||
| Compositional Zero-Shot Learning | VAW CZSL (test) | 30 | Mar 5, 2026 | ||
| Object Pose Estimation | OnePose | 30 | Feb 26, 2026 | ||
| Image Quality Assessment | PIPAL NTIRE 2022 IQA Challenge (test) | 30 | Feb 26, 2026 | ||
| Class-conditional Image Generation | ImageNet (train/val) | 30 | Feb 26, 2026 | ||
| Deepfake Detection | CelebDF (test) | 30 | Feb 26, 2026 | ||
| Image Generation | CIFAR-10 100% data | 30 | Feb 26, 2026 | ||
| Action Triplet Recognition | CholecT50 (test) | 30 | Feb 26, 2026 | ||
| Image Style Transfer | User Study | 30 | Feb 26, 2026 | ||
| 3D Dense Captioning | ScanRefer (test) | 30 | Feb 26, 2026 | ||
| Text Retrieval | Flickr30K (1K) | 30 | Feb 26, 2026 | ||
| Visual Grounding | ReferCOCO v1 (testB) | 30 | Feb 26, 2026 | ||
| Text Retrieval | Flickr30k Zero-shot (test) | 30 | Feb 26, 2026 | ||
| Skin Lesion Classification | ISIC 2018 (test) | 30 | May 12, 2026 | ||
| Adversarial Robustness | CIFAR-10 | 30 | Apr 28, 2026 | ||
| Aspect-Based Sentiment Analysis | SemEval Task 4 Subtask 2 Restaurant domain 2014 (test) | 30 | Feb 26, 2026 | ||
| Gaussian color image denoising | McMaster (test) | 30 | Feb 26, 2026 | ||
| Comment Classification | Civil Comments | 30 | Mar 4, 2026 | ||
| Image Classification | CIFAR-100 90% symmetric label noise | 30 | Apr 23, 2026 | ||
| Image Classification | CIFAR-100 80% symmetric label noise | 30 | Apr 23, 2026 | ||
| Speaker Identification | SID | 30 | Feb 26, 2026 | ||
| Natural Language Understanding | GLUE v1 (dev) | 30 | Feb 26, 2026 |