Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 655 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Hand-pose estimation | DexYCB S3 (test) | 36 | Feb 26, 2026 | ||
| Hand Pose Estimation | DexYCB (S0) | 36 | Feb 26, 2026 | ||
| Unsupervised Depth Completion | NYUv2 -> ScanNet -> VOID (Indoor Sequence) | 36 | Feb 27, 2026 | ||
| Cell Segmentation | Fluo-HeLa CTC (test) | 36 | Feb 26, 2026 | ||
| Mathematical Reasoning | Gaokao 2023 | 36 | Apr 23, 2026 | ||
| Image Super-Resolution | Set14 x3 scale (test) | 36 | May 26, 2026 | ||
| text-conditioned human interaction generation | InterHuman (test) | 36 | Jul 3, 2026 | ||
| Multiple Instance Learning Classification | ELEPHANT | 36 | Jun 5, 2026 | ||
| Code Reasoning | CRUXEval | 36 | May 27, 2026 | ||
| General Knowledge | HellaSwag | 36 | Apr 28, 2026 | ||
| Instruction Following | Super-Natural Instructions v2 (test) | 36 | Feb 26, 2026 | ||
| Vision-Language Evaluation | MME | 36 | May 8, 2026 | ||
| Image Classification | ImageNet (val) | 36 | Feb 26, 2026 | ||
| Box Inpainting | FFHQ 256x256-1K | 36 | Apr 29, 2026 | ||
| Question Answering | SQuAD | 36 | Feb 26, 2026 | ||
| Multimodal Capability Evaluation | MM-Star | 36 | Mar 4, 2026 | ||
| Natural Language Inference | MNLI | 36 | Feb 26, 2026 | ||
| People Identification | CSI People Identification Dataset | 36 | Feb 26, 2026 | ||
| Action Classification | CSI Action Classification Dataset | 36 | Feb 26, 2026 | ||
| Time-series Forecasting | Nasdaq | 36 | Feb 26, 2026 | ||
| Time-series Forecasting | NY-T | 36 | Feb 26, 2026 | ||
| Time-series Forecasting | NY-B | 36 | Feb 26, 2026 | ||
| Time-series Forecasting | PEM-B | 36 | Feb 26, 2026 | ||
| Time-series Forecasting | ETT2 | 36 | Apr 14, 2026 | ||
| Time-series Forecasting | Flu-Japan | 36 | Feb 26, 2026 |