Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 802 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Question Answering | OpenBookQA | 31 | Jul 3, 2026 | ||
| Shape Matching | SCAPE | 31 | Jun 26, 2026 | ||
| Referring Video Object Segmentation | MeViS | 31 | Jun 26, 2026 | ||
| Semi-supervised node classification | Arxiv (test) | 31 | Jun 23, 2026 | ||
| Semi-supervised node classification | Computers (test) | 31 | Jun 23, 2026 | ||
| Semi-supervised node classification | Cora (test) | 31 | Jun 23, 2026 | ||
| Training Efficiency Profiling | Qwen3 (train) | 31 | Jun 23, 2026 | ||
| Multi-task Image Restoration | All-in-One IR Benchmark Average | 31 | Jun 29, 2026 | ||
| Fold Classification | Fold Classification | 31 | Jun 23, 2026 | ||
| molecule question answering task | MoleculeQA | 31 | Jul 3, 2026 | ||
| Math Reasoning | MathVista GPS (test) | 31 | Jun 15, 2026 | ||
| Text Embedding | SkMTEB | 31 | Jun 12, 2026 | ||
| Open-domain Question Answering | Natural Questions | 31 | Jun 12, 2026 | ||
| Passage Retrieval | Natural Questions | 31 | Jun 12, 2026 | ||
| Question Answering | Natural Questions | 31 | Jun 12, 2026 | ||
| Mathematical Reasoning | HLE Maths | 31 | Jun 12, 2026 | ||
| Protein Property Prediction | 21 protein landscapes Unseen mutations 96 data points | 31 | Jun 11, 2026 | ||
| Image Super-Resolution | RealSet65 | 31 | Jun 11, 2026 | ||
| Robotic Manipulation | LIBERO | 31 | Jun 23, 2026 | ||
| Object Detection | MMIOC-1M closed scene | 31 | Jun 9, 2026 | ||
| Mathematical Reasoning | MMLU algebra | 31 | Jun 8, 2026 | ||
| Mathematical Reasoning | DART-Math (DM-1 to DM-5) | 31 | Jun 8, 2026 | ||
| Multimodal Sentiment Analysis | MOSI | 31 | Jun 5, 2026 | ||
| Image Classification | CIFAR-10-LT (gamma=200) (test) | 31 | Jun 4, 2026 | ||
| Image Classification | SynDigits-LT gamma=50 | 31 | Jun 4, 2026 |