Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 150 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Base-to-novel generalization | Food 101 | 91 | Jul 8, 2026 | ||
| JPEG compression artifact reduction | Classic5 | 91 | May 26, 2026 | ||
| Visual Question Answering | InfoVQA (val) | 91 | Apr 10, 2026 | ||
| Node Classification | Cora ML (test) | 91 | Jun 4, 2026 | ||
| Object Detection | Pascal VOC -> Clipart (test) | 91 | Mar 20, 2026 | ||
| Jailbreak Defense | GCG | 91 | Mar 19, 2026 | ||
| Medical Image Classification | COVID | 91 | May 27, 2026 | ||
| Class-conditional Image Generation | ImageNet 64x64 (test) | 91 | Apr 15, 2026 | ||
| Code Generation | MBPP-ET | 91 | Mar 4, 2026 | ||
| Clustering | DHA | 91 | Feb 26, 2026 | ||
| Super-resolution | DIV2K (val) | 91 | Mar 20, 2026 | ||
| Link Prediction | LastFM (inductive) | 91 | Jul 7, 2026 | ||
| Natural Language Understanding | SuperGLUE (dev) | 91 | Feb 27, 2026 | ||
| Image Classification | ImageNet-1K (val) | 91 | Feb 26, 2026 | ||
| 5-way few-shot classification | miniImageNet standard (test) | 91 | Feb 26, 2026 | ||
| Point Cloud Classification | ScanObjectNN PB_T50_RS (test) | 91 | Feb 26, 2026 | ||
| Object Detection | VOC 2007 (test) | 91 | May 21, 2026 | ||
| 3D Dense Captioning | ScanRefer (val) | 91 | May 12, 2026 | ||
| Image Generation | FFHQ | 91 | Apr 6, 2026 | ||
| Semantic Textual Similarity | STS-12 | 91 | May 29, 2026 | ||
| Node Classification | Cora (60/20/20 random split) | 91 | Mar 11, 2026 | ||
| Domain Generalization | VLCS (test) | 91 | Jul 3, 2026 | ||
| Facial Expression Recognition | AffectNet 7-way (test) | 91 | Feb 26, 2026 | ||
| Image Generation | MNIST | 91 | Jun 17, 2026 | ||
| 3D Hand Pose Estimation | ICVL (test) | 91 | Feb 26, 2026 |