Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 61 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Multimodal reasoning | MathVision | 162 | May 27, 2026 | ||
| Science Question Answering | ARC Easy | 162 | May 26, 2026 | ||
| Image Quality Assessment | PIPAL | 162 | Jun 16, 2026 | ||
| Image Classification | CIFAR10 non-iid | 162 | Mar 17, 2026 | ||
| Visual Active Search | DOTA | 162 | Feb 26, 2026 | ||
| Low-light Image Enhancement | LOL | 162 | Mar 10, 2026 | ||
| Question Answering | SQuAD | 162 | May 12, 2026 | ||
| Novel View Synthesis | LLFF 3-view | 162 | May 22, 2026 | ||
| Mathematical Reasoning | GSM-Hard | 162 | Apr 10, 2026 | ||
| Temporal Action Detection | ActivityNet 1.3 | 162 | Jun 11, 2026 | ||
| Node Classification | ogbn-products (test) | 162 | May 29, 2026 | ||
| Semantic Segmentation | Pascal VOC augmented 2012 (val) | 162 | Feb 26, 2026 | ||
| Graph Classification | CIFAR10 (test) | 162 | Jul 1, 2026 | ||
| Vision-Language Navigation | R2R (test unseen) | 162 | Jul 2, 2026 | ||
| Multimodal Emotion Recognition | IEMOCAP (test) | 162 | Mar 10, 2026 | ||
| Action Recognition | Something-Something V1 | 162 | Feb 26, 2026 | ||
| Panoptic Segmentation | COCO (test-dev) | 162 | Feb 26, 2026 | ||
| Sentiment Analysis | SST-2 (test) | 162 | Jun 4, 2026 | ||
| Domain Adaptation | Office-31 unsupervised adaptation standard | 162 | Feb 26, 2026 | ||
| Cardiac Segmentation | ACDC (test) | 162 | May 12, 2026 | ||
| Text Classification | AGNews | 161 | Jul 8, 2026 | ||
| Jailbreak Attack | MaliciousInstruct | 161 | Mar 27, 2026 | ||
| Monocular Depth Estimation | DIODE | 161 | Jun 12, 2026 | ||
| Node Classification | questions | 161 | Jul 9, 2026 | ||
| Text-to-Image Retrieval | COCO | 161 | Jul 2, 2026 |