Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2082 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Out-of-Distribution Detection | IMDB | 17 | Feb 26, 2026 | ||
| Out-of-Distribution Detection | News | 17 | Feb 26, 2026 | ||
| Out-of-Distribution Detection | Yelp | 17 | Feb 26, 2026 | ||
| Out-of-Distribution Detection | SST2 | 17 | Feb 26, 2026 | ||
| OOD Detection | IMDB (test) | 17 | Feb 26, 2026 | ||
| OOD Detection | NEWSTOP5 (test) | 17 | Feb 26, 2026 | ||
| OOD Detection | SST2 (test) | 17 | Feb 26, 2026 | ||
| Skeleton-based Action Recognition | Kinetics-Skeleton (test) | 17 | Feb 26, 2026 | ||
| Semantic Textual Similarity | MedSTS | 17 | Feb 26, 2026 | ||
| Response Generation | ReDial | 17 | Feb 26, 2026 | ||
| Point Cloud Semantic Segmentation | Water-surface dataset (test) | 17 | Feb 26, 2026 | ||
| Visual Place Recognition | San Francisco Landmark | 17 | Feb 26, 2026 | ||
| Hateful Meme Detection | MAMI | 17 | Mar 4, 2026 | ||
| Object Detection | PASCAL SBD 2012 | 17 | Feb 26, 2026 | ||
| Class-Incremental Learning | ImageNet-1K (test) | 17 | Feb 26, 2026 | ||
| Semantic Segmentation | IDD original size (val) | 17 | Feb 26, 2026 | ||
| Image-to-Text Retrieval | COCO 5K Full (test) | 17 | Feb 26, 2026 | ||
| Text-to-Image Retrieval | COCO 1K 5-fold (test) | 17 | Feb 26, 2026 | ||
| Image-to-Text Retrieval | COCO 1K 5-fold average (test) | 17 | Feb 26, 2026 | ||
| Skin Lesion Classification | Fitzpatrick-17k (test) | 17 | Feb 26, 2026 | ||
| Random Inpainting | FFHQ 256x256 (val) | 17 | Jun 30, 2026 | ||
| Semantic Parsing | GeoQuery (Len.) | 17 | Feb 26, 2026 | ||
| Autonomous Driving | Longest6 36 routes 1.0 | 17 | Feb 26, 2026 | ||
| Visual Question Answering | VQA + AdVQA 50/50 mix v2 (test) | 17 | Feb 26, 2026 | ||
| Visual Question Answering | 33.3% VQA v2 + 66.7% AdVQA (test) | 17 | Feb 26, 2026 |