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 |
|---|---|---|---|---|---|
| Question Answering | ARC-E | 544 | Jun 9, 2026 | ||
| Human-Object Interaction Detection | HICO-DET (test) | 544 | Jun 5, 2026 | ||
| Language Modeling | PTB (test) | 543 | May 27, 2026 | ||
| Anomaly Localization | MVTec-AD |
| 543 |
| Jun 30, 2026 |
| Node classification | ogbn-arxiv (test) | 542 | Jul 1, 2026 |
|---|
| Node Classification | CiteSeer | 541 | Jun 23, 2026 |
|---|
| Image Classification | RESISC45 | 539 | Jul 3, 2026 |
|---|
| Image Generation | CIFAR-10 (test) | 536 | Apr 28, 2026 |
|---|
| Mathematical Reasoning | MATH | 535 | Feb 26, 2026 |
|---|
| Class-conditional image generation | ImageNet 256x256 (val) | 535 | Jul 1, 2026 |
|---|
| Automatic Speech Recognition | LibriSpeech (dev-other) | 535 | Jul 1, 2026 |
|---|
| Anomaly Detection | ADBench noisy-context scenario 1.0 | 532 | Mar 17, 2026 |
|---|
| Graph Classification | COLLAB | 532 | Jul 3, 2026 |
|---|
| Multi-turn Dialogue Evaluation | MT-Bench | 532 | May 26, 2026 |
|---|
| Image Classification | UCF101 | 529 | Jun 9, 2026 |
|---|
| Natural Language Understanding | GLUE (dev) | 529 | Jun 19, 2026 |
|---|
| Text-to-Image Retrieval | Flickr30k (test) | 528 | Jun 30, 2026 |
|---|
| Long-term Time Series Forecasting | Weather | 527 | Jun 9, 2026 |
|---|
| 3D Human Pose Estimation | 3DPW (test) | 527 | Jun 30, 2026 |
|---|
| Semantic Segmentation | Cityscapes | 526 | Jul 8, 2026 |
|---|
| Mathematical Reasoning | AIME 2024 | 525 | Jun 19, 2026 |
|---|
| Visual Question Answering | ScienceQA | 525 | Jul 7, 2026 |
|---|
| Visual Question Answering | GQA | 524 | May 14, 2026 |
|---|
| Image-to-Text Retrieval | Flickr30K 1K (test) | 523 | Jul 3, 2026 |
|---|
| Instance Segmentation | COCO (val) | 520 | Jun 19, 2026 |
|---|