Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Language Modeling | WikiText2 | 4,085 | Jun 26, 2026 | ||
| Image Classification | CIFAR-100 (test) | 3,518 | Feb 26, 2026 | ||
| Image Classification | CIFAR-10 (test) | 3,381 | Feb 26, 2026 | ||
| Semantic Segmentation | ADE20K (val) | 3,089 | Jul 7, 2026 | ||
| Object Detection | COCO 2017 (val) | 2,930 | Jul 8, 2026 | ||
| Language Modeling | WikiText-2 | 2,862 | Jun 29, 2026 | ||
| Language Modeling | WikiText-2 (test) | 2,416 | Jul 9, 2026 | ||
| Image Classification | ImageNet-1K 1.0 (val) | 2,386 | Jun 24, 2026 | ||
| Semantic Segmentation | PASCAL VOC 2012 (val) | 2,210 | Jun 17, 2026 | ||
| Object Hallucination Evaluation | POPE | 2,056 | Jun 30, 2026 | ||
| Commonsense Reasoning | HellaSwag | 1,896 | May 11, 2026 | ||
| Visual Question Answering | VizWiz | 1,863 | Jul 3, 2026 | ||
| Language Modeling | C4 | 1,688 | May 21, 2026 | ||
| Commonsense Reasoning | WinoGrande | 1,581 | Jul 9, 2026 | ||
| Language Modeling | C4 | 1,565 | May 15, 2026 | ||
| Image Classification | ImageNet 1k (val) | 1,498 | Jun 1, 2026 | ||
| Semantic Segmentation | PASCAL VOC 2012 (test) | 1,485 | Jun 17, 2026 | ||
| Visual Question Answering | TextVQA | 1,455 | Jun 26, 2026 | ||
| Automatic Speech Recognition | LibriSpeech (test-other) | 1,447 | Jul 2, 2026 | ||
| Visual Question Answering | GQA | 1,445 | Jun 9, 2026 | ||
| Visual Question Answering | VQA v2 | 1,429 | Jun 2, 2026 | ||
| Mathematical Reasoning | GSM8K | 1,424 | Jul 1, 2026 | ||
| Automatic Speech Recognition | LibriSpeech clean (test) | 1,410 | Jul 2, 2026 | ||
| Graph Classification | PROTEINS | 1,383 | Jul 3, 2026 | ||
| Instance Segmentation | COCO 2017 (val) | 1,304 | Jul 3, 2026 |