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 |
|---|---|---|---|---|---|
| Hyperspectral Classification | WHU-Hi Hanchuan (test) | 31 | May 1, 2026 | ||
| Multimodal Visual Document Retrieval | MMEB Visual Document portion v2 | 31 | Apr 27, 2026 | ||
| Robotic Manipulation | SIMPLER Visual Matching | 31 | May 29, 2026 | ||
| Depth estimation | Hamlyn | 31 | Jun 16, 2026 | ||
| EEG Classification | Workload | 31 |
| May 14, 2026 |
| Image Generation | ImageNet-256 (test) | 31 | Jul 9, 2026 |
|---|
| Vision-Language Capability Evaluation | MME | 31 | Apr 21, 2026 |
|---|
| Generalized Category Discovery | FGVC-Aircraft (test) | 31 | May 12, 2026 |
|---|
| Control Task | Lunar Lander (test) | 31 | May 19, 2026 |
|---|
| 3D Brain Lesion Segmentation | S2 Sequence MSSEG, BRATS-Decathlon, ISLES, WMH, ATLAS | 31 | Apr 29, 2026 |
|---|
| Cardiac phenotype prediction | UKB dataset (test) | 31 | May 11, 2026 |
|---|
| Multi-robot path planning | TSPLIB 4 Robots | 31 | Feb 26, 2026 |
|---|
| Automatic Speech Recognition | Yodas (test) | 31 | Mar 5, 2026 |
|---|
| Multi-turn agent task | ACEBench multi-turn (test) | 31 | Apr 29, 2026 |
|---|
| Node Classification | CoauthorCS | 31 | Apr 13, 2026 |
|---|
| Causal Discovery | CE-Gauss | 31 | Apr 8, 2026 |
|---|
| POMDP Policy Optimization | Random POMDP | 31 | Feb 26, 2026 |
|---|
| Node Classification | DBLP | 31 | Jun 2, 2026 |
|---|
| Arithmetic Reasoning | AQuA, GSM8K, MAWPS, SVAMP | 31 | Mar 4, 2026 |
|---|
| Node Classification | PascalVOC-SP | 31 | Jun 4, 2026 |
|---|
| Text Generation | Text model inference M4 Max | 31 | Feb 26, 2026 |
|---|
| Mathematical Reasoning | GSM Hard | 31 | May 18, 2026 |
|---|
| Min-cost flow | Road network large-scale instances | 31 | Feb 26, 2026 |
|---|
| Graph Classification | PCBA | 31 | Jun 2, 2026 |
|---|
| Common Sense Reasoning | ARC-Challenge 0-shot | 31 | Apr 9, 2026 |
|---|