Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 989 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Omnidirectional Image Super-Resolution | Flickr360 (test) | 27 | Jun 30, 2026 | ||
| Complex Reasoning | GraphRAG-Bench | 27 | Jun 30, 2026 | ||
| Model Attribution | 8-model closed-set attribution task Ntest=500 per model (test) | 27 | Jun 29, 2026 | ||
| Slice Super-Resolution | Hepatic Vessels (test) | 27 | Jun 26, 2026 | ||
| Slice Super-Resolution | Liver (test) | 27 | Jun 26, 2026 | ||
| Slice Super-Resolution | Colon (test) | 27 | Jun 26, 2026 | ||
| Inverse design | Nanophotonics structures | 27 | Jun 25, 2026 | ||
| Forecasting | Solar-Energy (test) | 27 | Jun 25, 2026 | ||
| Spatiotemporal Forecasting | Solar-Energy (test) | 27 | Jun 25, 2026 | ||
| Image Classification | CIFAR-10 (test) | 27 | Jun 25, 2026 | ||
| Image Classification | ImageNet | 27 | Jun 25, 2026 | ||
| Binary Classification | UCI HAR 2Classes | 27 | Jun 23, 2026 | ||
| Binary Classification | MNIST 2Classes | 27 | Jun 23, 2026 | ||
| Binary Classification | ISOLET 2Classes | 27 | Jun 23, 2026 | ||
| Image Generation | CC3M SDXL v1.0 (test) | 27 | Jun 23, 2026 | ||
| Aesthetic Evaluation | CC3M SDXL 1.0 (test) | 27 | Jun 23, 2026 | ||
| Legal Judgment Prediction | ECHR (test) | 27 | Jun 23, 2026 | ||
| Legal Judgment Prediction | ILDC (test) | 27 | Jun 23, 2026 | ||
| Dust emission forecasting | Dust emission forecasting dataset | 27 | Jun 19, 2026 | ||
| Foreground Rendering | DTU | 27 | Jun 18, 2026 | ||
| Research method classification | LIS research method dataset (test) | 27 | Jun 18, 2026 | ||
| Mathematical Reasoning | AIME25 | 27 | Jun 18, 2026 | ||
| Object Detection | Cityscapes-to-Cityscapes long-term CTTA task C | 27 | Jun 18, 2026 | ||
| Question Answering | ARC Easy | 27 | Jun 18, 2026 | ||
| Question Answering | ARC Challenge | 27 | Jun 18, 2026 |