Loading the SOTA2 catalog…
SOTA2 Research · benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
| Task | Dataset | Domain | Trend | Results | Last Update |
|---|---|---|---|---|---|
| Image Classification | ImageNet-R | 622 | Jul 2, 2026 | ||
| Visual Question Answering | ChartQA | 620 | Jul 8, 2026 | ||
| Video Instance Segmentation | YouTube-VIS 2019 (val) |
| 620 |
| Jun 19, 2026 |
| Image Classification | DTD | 610 | Jun 4, 2026 |
|---|
| Node Classification | Cora | 609 | Jun 4, 2026 |
|---|
| Text-to-Image Retrieval | Flickr30K | 607 | Jun 30, 2026 |
|---|
| Image Generation | ImageNet 256x256 | 606 | Jul 3, 2026 |
|---|
| 3D Human Pose Estimation | MPI-INF-3DHP (test) | 606 | May 13, 2026 |
|---|
| Action Recognition | NTU RGB+D 60 (cross-view) | 601 | Jun 2, 2026 |
|---|
| Mathematical Reasoning | MATH 500 | 600 | Jun 19, 2026 |
|---|
| Long-term Time Series Forecasting | ETTh1 | 600 | Jun 26, 2026 |
|---|
| Image Classification | ImageNet-1k | 600 | Mar 27, 2026 |
|---|
| node classification | Actor | 598 | Jun 25, 2026 |
|---|
| Image Classification | Clothing1M (test) | 598 | May 4, 2026 |
|---|
| Question Answering | ARC Easy | 597 | Jun 5, 2026 |
|---|
| Multivariate Time Series Forecasting | ETTm2 | 593 | Jun 25, 2026 |
|---|
| Medical Question Answering | MedMCQA | 591 | Jul 1, 2026 |
|---|
| Natural Language Inference | RTE | 590 | May 28, 2026 |
|---|
| Image Classification | Food-101 | 590 | Jul 2, 2026 |
|---|
| Mathematical Reasoning | MATH 500 | 589 | Jun 26, 2026 |
|---|
| Question Answering | PIQA | 589 | Jul 7, 2026 |
|---|
| Semantic Segmentation | GTA5 → Cityscapes (val) | 586 | Mar 18, 2026 |
|---|
| Image Classification | CIFAR10 (test) | 585 | Feb 26, 2026 |
|---|
| Fine-grained Image Classification | CUB200 2011 (test) | 585 | Jun 30, 2026 |
|---|
| Text-to-image generation | GenEval | 581 | Jul 7, 2026 |
|---|