Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 10 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Optical Character Recognition | OCRBench | 486 | Jul 7, 2026 | ||
| Visual Question Answering | VQA v2 (test-std) | 486 | Apr 13, 2026 | ||
| Language Modeling | C4 | 482 | Jul 7, 2026 | ||
| GUI Grounding | ScreenSpot Pro | 482 | Jun 30, 2026 | ||
| Time Series Forecasting | ETTh1 (test) | 482 | Jul 3, 2026 | ||
| Action Recognition | NTU RGB+D X-sub 120 | 482 | Jul 2, 2026 | ||
| Semantic Segmentation | SYNTHIA to Cityscapes (val) | 480 | Mar 18, 2026 | ||
| Long-term Time Series Forecasting | ETTm2 | 479 | Jun 16, 2026 | ||
| Text-to-SQL | BIRD (dev) | 477 | Jul 7, 2026 | ||
| Vision-and-Language Navigation | R2R (val unseen) | 476 | Jul 7, 2026 | ||
| Long-term Time Series Forecasting | ETTh2 | 474 | Jun 26, 2026 | ||
| Text-to-Video Retrieval | DiDeMo | 472 | Jul 2, 2026 | ||
| Image-to-Text Retrieval | Flickr30k (test) | 472 | Jun 30, 2026 | ||
| Multivariate long-term series forecasting | ETTh2 | 470 | Jun 29, 2026 | ||
| Image Classification | SVHN (test) | 470 | May 22, 2026 | ||
| Visual Object Tracking | LaSOT (test) | 470 | May 27, 2026 | ||
| Multivariate Time Series Forecasting | Weather | 466 | Jun 25, 2026 | ||
| Super-resolution | B100 | 465 | May 22, 2026 | ||
| Question Answering | OpenBookQA | 465 | Feb 26, 2026 | ||
| Long-term Time Series Forecasting | ETTm1 | 463 | Jun 9, 2026 | ||
| Physical Interaction Question Answering | PIQA | 462 | Jul 2, 2026 | ||
| Image Classification | FashionMNIST (test) | 461 | Jul 9, 2026 | ||
| Visual Object Tracking | GOT-10k (test) | 461 | Jul 8, 2026 | ||
| Image Generation | ImageNet 256x256 (val) | 461 | Jul 3, 2026 | ||
| Audio Classification | ESC-50 | 461 | Jun 9, 2026 |