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 |
|---|---|---|---|---|---|
| Continuous Control | LunarLanderContinuous offline trajectories v2 | 35 | Feb 26, 2026 | ||
| Node classification | ogbn-proteins | 35 | Feb 26, 2026 | ||
| Video Grounding | MAD (test) | 35 | Feb 26, 2026 | ||
| Short-term forecasting | M4 (test) | 35 | Feb 26, 2026 | ||
| Multilingual Mathematical Reasoning | MGSM 1.0 (test) | 35 | Feb 26, 2026 | ||
| Commonsense Reasoning |
|---|
| XCOPA |
| 35 |
| Apr 23, 2026 |
| Cell Segmentation | MoNuSeg | 35 | May 29, 2026 |
|---|
| Neural Code Search | Neural Code Search (NCS) (test) | 35 | Feb 26, 2026 |
|---|
| Task-incremental learning | Split Tiny-ImageNet (test) | 35 | Jun 9, 2026 |
|---|
| Image forgery localization | DSO-1 | 35 | Jun 24, 2026 |
|---|
| Automatic Speech Recognition | AISHELL-2 (test_ios) | 35 | Apr 21, 2026 |
|---|
| Factual Consistency Evaluation | QAGS-XSum (test) | 35 | Jun 26, 2026 |
|---|
| ASR Rescoring | WSJ (test) | 35 | Feb 26, 2026 |
|---|
| Automatic Speech Recognition | LibriSpeech 960h clean (dev) | 35 | Jun 11, 2026 |
|---|
| Sign Language Translation | OpenASL (dev) | 35 | Apr 21, 2026 |
|---|
| Graph Regression | Peptides-struct LRGB | 35 | Mar 4, 2026 |
|---|
| Graph Classification | Peptides-func LRGB | 35 | Mar 4, 2026 |
|---|
| Visual Object Tracking | AVisT (test) | 35 | Feb 26, 2026 |
|---|
| Few-Shot Image Generation | Babies 10-shot | 35 | Feb 26, 2026 |
|---|
| Image Classification | ImageNet (test) | 35 | Mar 12, 2026 |
|---|
| Relation Extraction | TACRED-Revisit | 35 | Feb 26, 2026 |
|---|
| Surface Reconstruction | DTU 1.0 (test) | 35 | Feb 26, 2026 |
|---|
| Video Compression | UVG (test) | 35 | May 21, 2026 |
|---|
| Visual Localization | Cambridge Landmarks Church | 35 | Apr 8, 2026 |
|---|
| Visual Localization | Cambridge Landmarks College | 35 | Apr 8, 2026 |
|---|