Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 809 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Text Rendering | LongText-Bench | 31 | May 26, 2026 | ||
| Simultaneous Localization and Mapping | Authors' New Aerial Dataset | 31 | Mar 10, 2026 | ||
| Aspect-Based Sentiment Analysis | Rest 14 | 31 | May 21, 2026 | ||
| Deblurring | BSD68 | 31 | Jun 5, 2026 | ||
| Medical Image Segmentation | CAMUS | 31 | Jul 7, 2026 | ||
| Federated Continual Learning | CIFAR-100 | 31 | Jun 11, 2026 | ||
| Federated Continual Learning | ImageNet R | 31 | Jun 11, 2026 | ||
| GUI Interaction Control | GUI-Odyssey | 31 | Apr 27, 2026 | ||
| 5-way Few-shot Image Classification | ISIC | 31 | Mar 6, 2026 | ||
| Medical Question Answering | MedXpertQA | 31 | Mar 31, 2026 | ||
| Grayscale Image Denoising | Urban100 105 (test) | 31 | Mar 4, 2026 | ||
| Grayscale Image Denoising | BSD68 104 (test) | 31 | Mar 4, 2026 | ||
| Grayscale Image Denoising | Set12 8 (test) | 31 | Mar 4, 2026 | ||
| Unconditional generation | LM1B | 31 | May 12, 2026 | ||
| Continual Learning | CIFAR-10 (test) | 31 | Mar 4, 2026 | ||
| Machine Translation | Multi30K eng → deu 2017 (test) | 31 | Jun 16, 2026 | ||
| Machine Translation | Multi30K eng → deu 2016 (test) | 31 | Jun 16, 2026 | ||
| Language Understanding and Reasoning | LLM Evaluation Suite MMLU, GSM8k, HellaSwag, WinoGrande | 31 | Mar 4, 2026 | ||
| Question Answering | Medical | 31 | Jun 16, 2026 | ||
| Lossless compression | Kodak | 31 | Mar 31, 2026 | ||
| Memory-augmented language modeling evaluation | LONGMEMEVAL-S | 31 | Mar 4, 2026 | ||
| Research Idea Evaluation | ScholarIdeas-AI contribution rubrics | 31 | Mar 4, 2026 | ||
| Multimodal Mathematical Reasoning | DynaMath | 31 | May 11, 2026 | ||
| Image Classification | CIFAR-10 (test) | 31 | Feb 27, 2026 | ||
| Pose estimation | MegaDepth | 31 | Feb 27, 2026 |