Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 4 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|
| Image Classification | Tiny-ImageNet (test) | computer vision | | 859 | Jul 7, 2026 |
|---|
| Node Classification | Texas | graph | | 859 | Jun 30, 2026 |
|---|
| Instruction Following | IFEval | llm chat instruction | | 854 | Jun 26, 2026 |
|---|
| Super-Resolution | Set5 | computer vision | | 854 | Jul 7, 2026 |
|---|
| Language Understanding | MMLU | nlp | | 844 | May 12, 2026 |
|---|
| Object Detection | PASCAL VOC 2007 (test) | computer vision | | 844 | Mar 17, 2026 |
|---|
| Mathematical Reasoning | GSM8K (test) | llm chat instructionnlp | | 816 | May 8, 2026 |
|---|
| Node Classification | Squirrel | graph | | 815 | Jun 25, 2026 |
|---|
| Time Series Forecasting | ETTh2 | tabular time series | | 796 | May 26, 2026 |
|---|
| Image Classification | CIFAR-100 (val) | computer vision | | 781 | Jun 18, 2026 |
|---|
| Action Recognition | NTU RGB+D 120 (X-set) | computer vision | | 779 | Jul 2, 2026 |
|---|
| Vision-Language Navigation | R2R-CE (val-unseen) | robotics embodied aimultimodal | | 779 | Jul 8, 2026 |
|---|
| Image Super-resolution | Set5 | computer vision | | 774 | May 26, 2026 |
|---|
| Language Modeling | WikiText-103 (test) | nlp | | 773 | Jun 29, 2026 |
|---|
| Reasoning | BBH | llm chat instructionnlp | | 770 | Jun 29, 2026 |
|---|
| Image Classification | ImageNet V2 | computer vision | | 767 | Jul 9, 2026 |
|---|
| Commonsense Reasoning | PIQA | nlp |
| 757 | May 18, 2026 |
|---|
| Instruction Following | AlpacaEval 2.0 | llm chat instruction | | 752 | Jun 12, 2026 |
|---|
| Multivariate Time-series Forecasting | ETTm1 | tabular time series |
| 742 | Jun 25, 2026 |
|---|
| Language Modeling | WikiText | nlp | | 740 | May 13, 2026 |
|---|
| Physical Commonsense Reasoning | PIQA | nlp | | 724 | Jun 24, 2026 |
|---|
| Image Classification | ImageNet A | computer vision | | 723 | Jul 2, 2026 |
|---|
| Visual Question Answering | VQA v2 (test-dev) | multimodalcomputer vision+1 | | 721 | Jun 19, 2026 |
|---|
| Graph Classification | NCI1 | graph | | 707 | Jul 3, 2026 |
|---|
| Image Classification | ImageNet 1k (val) | computer vision | | 706 | Feb 26, 2026 |
|---|