Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 16 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Mathematical Reasoning | AIME 2024 | 370 | Mar 25, 2026 | ||
| Long-context Language Modeling | LongBench | 369 | Jun 30, 2026 | ||
| Video Understanding | VideoMME | 369 | Jul 1, 2026 | ||
| Salient Object Detection | DUTS (test) | 368 | Jun 19, 2026 | ||
| Super-Resolution | Manga109 | 368 | May 26, 2026 | ||
| Class-conditional image generation | ImageNet 256x256 (train) | 367 | Jun 11, 2026 | ||
| Object Hallucination | POPE Adversarial | 367 | Jun 11, 2026 | ||
| Commonsense Reasoning | CSQA | 366 | Feb 26, 2026 | ||
| Image Classification | ImageNet | 366 | Mar 10, 2026 | ||
| Action Recognition | Something-Something V2 | 363 | May 12, 2026 | ||
| Link Prediction | FB15k-237 | 363 | Jun 19, 2026 | ||
| Time Series Forecasting | ETTm1 | 363 | Jun 1, 2026 | ||
| Image Classification | CIFAR-100 | 362 | Jun 26, 2026 | ||
| 3D Object Detection | ScanNet V2 (val) | 361 | Apr 10, 2026 | ||
| Semantic Segmentation | PASCAL Context (val) | 360 | Apr 3, 2026 | ||
| Multivariate Forecasting | ETTh2 | 359 | May 12, 2026 | ||
| Image Classification | VTAB 1k | 359 | Jul 9, 2026 | ||
| Mathematical Reasoning | AIME 24 | 358 | Jun 18, 2026 | ||
| Mathematical Reasoning | GSM8K | 358 | Feb 26, 2026 | ||
| Action Recognition | NTU RGB-D Cross-Subject 60 | 358 | Jun 2, 2026 | ||
| Part Segmentation | ShapeNetPart (test) | 358 | Jun 15, 2026 | ||
| Science Question Answering | ScienceQA IMG | 357 | Jul 9, 2026 | ||
| Image Classification | Office-31 | 357 | Jun 8, 2026 | ||
| Action Recognition | UCF101 (mean of 3 splits) | 357 | Feb 26, 2026 | ||
| Image Retrieval | Flickr30k (test) | 357 | Jun 11, 2026 |