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 |
|---|---|---|---|---|---|
| Generation | DROP | 49 | Jun 5, 2026 | ||
| Text Anomaly Detection | AGNews | 49 | May 29, 2026 | ||
| Long-context evaluation | RULER 32k | 49 | May 19, 2026 | ||
| Machine Translation | WMT24++ v1.0 (test) | 49 | Feb 26, 2026 | ||
| Summarization | TL;DR (test) | 49 | Feb 26, 2026 | ||
| Question Answering | General QA NQ, TriviaQA, PopQA (test) |
| 49 |
| Feb 26, 2026 |
| Reasoning | BBH | 49 | May 27, 2026 |
|---|
| Node Classification | Amazon-ratings heterophilic (test) | 49 | Apr 13, 2026 |
|---|
| Node Classification | Roman-empire heterophilic (test) | 49 | Apr 13, 2026 |
|---|
| Video Generation | VBench Long | 49 | May 26, 2026 |
|---|
| Homography Estimation | RGB NIR | 49 | Mar 5, 2026 |
|---|
| Novel View Synthesis | ActorsHQ | 49 | Jun 19, 2026 |
|---|
| Time Series Forecasting | M5 | 49 | Apr 14, 2026 |
|---|
| Mathematics | AIME 2024 | 49 | Mar 4, 2026 |
|---|
| Question Answering | GPQA Diamond | 49 | Feb 26, 2026 |
|---|
| Open-set ObjectGoal Navigation | HM3D-OVON unseen (val) | 49 | Apr 24, 2026 |
|---|
| Object-level Anomaly Detection | Anomaly-ShapeNet (test) | 49 | Feb 26, 2026 |
|---|
| Image Denoising | FMDD | 49 | Jun 23, 2026 |
|---|
| Image Classification | ImageNet-1K (val) | 49 | Jul 3, 2026 |
|---|
| Planning | nuPlan 14 Random (test) | 49 | Mar 16, 2026 |
|---|
| Optical Character Recognition | OCRBench (test) | 49 | Jun 2, 2026 |
|---|
| Open-ended Generation | AlpacaEval 2.0 | 49 | Jul 7, 2026 |
|---|
| Alignment | MT-Bench | 49 | May 1, 2026 |
|---|
| Medical Image Segmentation | RSNA Pneumonia | 49 | Feb 27, 2026 |
|---|
| Image Clustering | DTD | 49 | Apr 14, 2026 |
|---|