Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 132 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Patient-to-room assignment | IHTC 2024 | 98 | May 4, 2026 | ||
| Novel View Synthesis | Mip-NeRF 360 | 98 | Jul 7, 2026 | ||
| Image Classification | SVHN (test) | 98 | Jun 16, 2026 | ||
| Image Classification | Stanford Cars | 98 | May 20, 2026 | ||
| Image Classification | CIFAR-100 (test) | 98 | Jun 29, 2026 | ||
| Precipitation Nowcasting | ERA5 | 98 | Mar 17, 2026 | ||
| Mathematical Reasoning | GSM8K | 98 | Jun 12, 2026 | ||
| Heart Rate Estimation | BUAA | 98 | Apr 14, 2026 | ||
| OCR Performance Evaluation | OCRBench | 98 | Jun 9, 2026 | ||
| Multi-modal Question Answering | MMMU | 98 | Jun 8, 2026 | ||
| Multi-Agent Path Finding | Maze Map | 98 | Feb 27, 2026 | ||
| Multi-Agent Path Finding | Random Map | 98 | Feb 27, 2026 | ||
| Multi-Agent Path Finding | Room Map | 98 | Feb 27, 2026 | ||
| Language Understanding | MMLU | 98 | Mar 9, 2026 | ||
| Robot Dynamics Modeling | WAM (test) | 98 | Feb 26, 2026 | ||
| Image Generation | MNIST Binary (test) | 98 | Feb 26, 2026 | ||
| WSI Classification | NTUH-Ki67-Liver (5-fold cross-val) | 98 | Feb 26, 2026 | ||
| Watermark extraction | COCO | 98 | Feb 26, 2026 | ||
| Drone-to-Satellite Retrieval | SUES-200 150m | 98 | Apr 3, 2026 | ||
| Image Classification | ImageNet-A | 98 | Jun 8, 2026 | ||
| Polish Text Understanding | CPTUB | 98 | Apr 14, 2026 | ||
| Knowledge | MMLU-Pro | 98 | Jul 7, 2026 | ||
| Safety Evaluation | MM-SafetyBench | 98 | May 28, 2026 | ||
| Image Editing | KRIS-Bench | 98 | May 15, 2026 | ||
| Truthfulness | TruthfulQA | 98 | Jun 4, 2026 |