Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 25 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Image Classification | CIFAR10 | 282 | Jun 2, 2026 | ||
| Long Video Understanding | LongVideoBench (val) | 282 | Jun 26, 2026 | ||
| Image Clustering | STL-10 | 282 | May 12, 2026 | ||
| Few-shot classification | tieredImageNet (test) | 282 | Feb 26, 2026 | ||
| Scientific Question Answering | ScienceQA image | 281 | Jul 9, 2026 | ||
| Class Incremental Learning | CIFAR-100 | 281 | Jun 11, 2026 | ||
| Domain Generalization | PACS (test) | 281 | Jul 3, 2026 | ||
| Hallucination Evaluation | POPE | 281 | Jul 8, 2026 | ||
| Text-to-image generation | Stable Diffusion v1.4 | 280 | Mar 17, 2026 | ||
| Deraining | Rain100L | 280 | May 19, 2026 | ||
| Mathematical Reasoning | ASDiv | 280 | Jun 8, 2026 | ||
| Common Sense Reasoning | BoolQ | 280 | Jul 7, 2026 | ||
| Mathematical Reasoning | MAWPS | 279 | Jul 2, 2026 | ||
| Object Counting | FSC-147 (val) | 279 | Jun 24, 2026 | ||
| Image Classification | PACS (test) | 279 | May 11, 2026 | ||
| Video Question Answering | MSVD-QA (test) | 279 | Mar 26, 2026 | ||
| Crowd Counting | ShanghaiTech Part A (test) | 279 | Jun 24, 2026 | ||
| Reading Comprehension | BOOLQ | 279 | Mar 12, 2026 | ||
| Language Generation | C4 | 278 | Jun 5, 2026 | ||
| Zero-shot Evaluation | Downstream Tasks Zero-shot | 278 | Feb 26, 2026 | ||
| Change Detection | WHU-CD | 278 | Jul 7, 2026 | ||
| Mathematical Multimodal Reasoning | MathVista | 276 | Jun 19, 2026 | ||
| Jailbreak Attack | HarmBench (test) | 276 | Jun 16, 2026 | ||
| Text-based Visual Question Answering | TextVQA (val) | 276 | Jun 2, 2026 | ||
| Summarization | XSum (test) | 276 | May 29, 2026 |