Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 192 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Planning | NAVSIM (navtest) | 78 | Jun 16, 2026 | ||
| Few-shot Semantic Segmentation | COCO-20i (val) | 78 | Feb 26, 2026 | ||
| Feature Importance Assessment | ImageNet 1k (val) | 78 | Feb 26, 2026 | ||
| Code Generation | HumanEval and MBPP | 78 | Jun 19, 2026 | ||
| Mathematical Reasoning | DeepMind-Mathematics | 78 | Jun 9, 2026 | ||
| Multimodal Reasoning | MMMU | 77 | Jul 1, 2026 | ||
| Brain-to-image retrieval | THINGS-EEG2 Intra-subject v1 (test) | 77 | Apr 21, 2026 | ||
| Node Classification | Toys | 77 | Jul 1, 2026 | ||
| Point Cloud Registration | 3DLoMatch | 77 | Jul 2, 2026 | ||
| Image Classification | Fashion-MNIST | 77 | Apr 7, 2026 | ||
| Image Classification | CIFAR-100 (test) | 77 | Apr 7, 2026 | ||
| Image Classification | CIFAR-10 | 77 | Apr 7, 2026 | ||
| XR Text Entry | Various XR Text-Entry User Studies Survey Table 2012-2024 | 77 | Jun 9, 2026 | ||
| Model Merging | 8 Vision tasks (test) | 77 | May 14, 2026 | ||
| Long-Form Video Understanding | LVBench | 77 | Jul 7, 2026 | ||
| Scientific Reasoning | GPQA-D | 77 | May 12, 2026 | ||
| Tactile Recognition | Closed-set 36-category tactile dataset 1.0 (test) | 77 | Mar 10, 2026 | ||
| Interactive Decision Making | WebShop | 77 | Jul 7, 2026 | ||
| Multimodal Perception Assessment | MME Perception | 77 | May 27, 2026 | ||
| OCR & Document Understanding | OCRBench | 77 | Jul 1, 2026 | ||
| Minutiae Extraction | NIST SD27 (test) | 77 | Mar 20, 2026 | ||
| Counterfactual Outcome Estimation | Tumor Growth tau=2 synthetic (test) | 77 | Feb 26, 2026 | ||
| Question Answering | SimpleQA Verified | 77 | Jun 23, 2026 | ||
| Classification | OASIS-3 (test) | 77 | May 14, 2026 | ||
| Uncertainty Estimation | JudgeBench (test) | 77 | Feb 26, 2026 |