Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 7 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| text-to-motion generation | HumanML3D (test) | 576 | Jun 16, 2026 | ||
| Semantic Segmentation | Cityscapes (val) | 572 | Feb 26, 2026 | ||
| Classification | Cars | 571 | Jul 9, 2026 | ||
| Multimodal Understanding | SEED-Bench | 571 | Jun 24, 2026 | ||
| Robotic Manipulation | LIBERO | 570 | Jun 26, 2026 | ||
| 3D Human Pose Estimation | Human3.6M (test) | 570 | Jun 30, 2026 | ||
| Image Classification | EuroSAT | 569 | Apr 3, 2026 | ||
| Multitask Language Understanding | MMLU | 568 | Jun 9, 2026 | ||
| Mathematical Reasoning | MathVista | 566 | Jun 19, 2026 | ||
| Image Super-Resolution | Set14 | 565 | May 26, 2026 | ||
| Action Recognition | Something-Something v2 (val) | 565 | Jun 25, 2026 | ||
| Video Object Segmentation | DAVIS 2016 (val) | 564 | Mar 4, 2026 | ||
| Image Classification | CIFAR-10 | 564 | Mar 17, 2026 | ||
| Image Classification | TinyImageNet (test) | 562 | Jun 25, 2026 | ||
| Multi-hop Question Answering | 2WikiMultiHopQA | 559 | May 20, 2026 | ||
| Image Classification | Flowers102 | 558 | Mar 27, 2026 | ||
| Multi-Object Tracking | DanceTrack (test) | 557 | Jul 2, 2026 | ||
| Named Entity Recognition | CoNLL 2003 (test) | 556 | Jun 4, 2026 | ||
| Semantic Segmentation | Cityscapes (val) | 552 | Jun 29, 2026 | ||
| Monocular Depth Estimation | KITTI (Eigen) | 552 | Jul 2, 2026 | ||
| Time Series Forecasting | ETTm2 | 552 | Jun 16, 2026 | ||
| Natural Language Understanding | GLUE | 551 | May 13, 2026 | ||
| Multimodal Reasoning | MM-Vet | 551 | Jul 3, 2026 | ||
| Object Detection | LVIS v1.0 (val) | 548 | Jul 8, 2026 | ||
| Person Re-identification | MSMT17 | 546 | Jun 2, 2026 |