Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 9 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Object Tracking | LaSOT | 519 | Jul 3, 2026 | ||
| Person Re-identification | MSMT17 (test) | 517 | May 4, 2026 | ||
| Video Question Answering | MSRVTT-QA | 513 | Jun 23, 2026 | ||
| Vision-Language Navigation | RxR-CE (val-unseen) | 512 | Jul 8, 2026 | ||
| Action Recognition | NTU RGB+D (Cross-subject) | 511 | Jun 4, 2026 | ||
| Multimodal Understanding | MMStar | 511 | Jul 3, 2026 | ||
| Text-to-Image Generation | DPG-Bench | 510 | Jun 30, 2026 | ||
| Multivariate long-term forecasting | ETTh1 | 509 | Jul 2, 2026 | ||
| Diagram Question Answering | AI2D | 509 | Jul 7, 2026 | ||
| Image Classification | CIFAR-10 | 507 | Feb 26, 2026 | ||
| Action Recognition | Kinetics-400 | 505 | Jun 4, 2026 | ||
| Change Detection | LEVIR-CD (test) | 503 | Jun 23, 2026 | ||
| Visual Object Tracking | TrackingNet (test) | 502 | May 22, 2026 | ||
| Node Classification | Pubmed | 501 | Jun 30, 2026 | ||
| Long-term forecasting | ETTh1 | 500 | Jul 9, 2026 | ||
| Single Image Super-Resolution | Urban100 | 500 | Feb 26, 2026 | ||
| Object Detection | COCO v2017 (test-dev) | 499 | Feb 26, 2026 | ||
| Mathematical Reasoning | GSM8K | 499 | Mar 25, 2026 | ||
| Time Series Forecasting | Weather | 497 | May 19, 2026 | ||
| Action Recognition | NTU RGB+D 60 (X-sub) | 496 | May 22, 2026 | ||
| Video Object Segmentation | YouTube-VOS 2018 (val) | 493 | Feb 26, 2026 | ||
| Image Classification | ImageNet-Sketch | 491 | Jul 7, 2026 | ||
| Image Classification | ImageNet-1K (test) | 490 | Jul 2, 2026 | ||
| Language Modeling | C4 (test) | 488 | Jun 11, 2026 | ||
| Image Classification | DTD | 487 | Apr 24, 2026 |