Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 184 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Text-to-image person retrieval | RSTPReid | 80 | Jun 30, 2026 | ||
| End-to-end scene text spotting | Total-Text | 80 | Apr 23, 2026 | ||
| Text Classification | SST-2 | 80 | Jun 4, 2026 | ||
| Sentiment Classification | SST-2 64 instances (test) | 80 | Feb 26, 2026 | ||
| Adversarial Attack | ImageNet 21k (val) | 80 | Feb 26, 2026 | ||
| Unconditional Image Generation | FFHQ 256x256 | 80 | May 12, 2026 | ||
| Image Classification | ImageNet-1K 1.0 (val) | 80 | Feb 26, 2026 | ||
| Time Series Classification | Handwriting | 80 | Jun 4, 2026 | ||
| Open-Domain Question Answering | TriviaQA (test) | 80 | Feb 26, 2026 | ||
| Weakly-Supervised Object Localization | CUB (test) | 80 | Feb 26, 2026 | ||
| Natural Language Inference | MNLI | 80 | Jun 8, 2026 | ||
| Video Person Re-ID | iLIDS-VID | 80 | Feb 26, 2026 | ||
| Node Classification | ACM-3 | 80 | Feb 26, 2026 | ||
| Classification | Diabetes | 80 | May 20, 2026 | ||
| Story completion | StoryCloze | 80 | May 4, 2026 | ||
| Dependency Parsing | Penn Treebank (PTB) (test) | 80 | Feb 26, 2026 | ||
| Object Localization | ImageNet-1k (val) | 80 | Feb 26, 2026 | ||
| Named Entity Recognition | BC5CDR (test) | 80 | Feb 26, 2026 | ||
| Multi-view 3D Reconstruction | ShapeNet r2n2 13 categories (test) | 80 | Feb 26, 2026 | ||
| Person Re-identification | Market-1501 (train) | 80 | Feb 26, 2026 | ||
| Gait Recognition | CASIA-B NM (Normal) (NM#5-6 probe) | 80 | May 15, 2026 | ||
| Image Classification | CIFAR10 (test) | 80 | Feb 26, 2026 | ||
| Crowd Counting | WorldExpo'10 (test) | 80 | Feb 26, 2026 | ||
| Temporal Action Detection | ActivityNet 1.3 (test) | 80 | Feb 27, 2026 | ||
| 3D Object Reconstruction | ShapeNet (test) | 80 | Feb 26, 2026 |