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 |
|---|---|---|---|---|---|
| Tensor Completion | News 144 x 176 x 100 | 35 | Mar 4, 2026 | ||
| Tensor Completion | Botswana 256 x 256 x 145 | 35 | Mar 4, 2026 | ||
| Tensor Completion | Washington DC 256 x 256 x 191 | 35 | Mar 4, 2026 | ||
| Tensor Completion | Flowers 256 x 256 x 31 | 35 | Mar 4, 2026 | ||
| Tensor Completion | Toys 256 x 256 x 31 | 35 | Mar 4, 2026 | ||
| Multi-modal Vehicle Re-Identification |
| MSVR310 (test) |
| 35 |
| Jun 19, 2026 |
| Single-hop Question Answering | Single-hop QA Average | 35 | Mar 19, 2026 |
|---|
| UI Grounding | UI-Vision | 35 | May 14, 2026 |
|---|
| Fine-grained classification | Aircraft | 35 | Jun 8, 2026 |
|---|
| Few-shot Image Classification | miniImageNet Open-Ended 2-Way | 35 | Feb 27, 2026 |
|---|
| Few-shot Classification | miniImageNet Open-Ended 5-Way (test) | 35 | Feb 27, 2026 |
|---|
| Image Classification | MNIST (test) | 35 | Feb 27, 2026 |
|---|
| Natural Language Code Search | CodeSearchNet | 35 | Jun 2, 2026 |
|---|
| Image Reconstruction | Gen3-DroneFlight Max Speed 1 m/s | 35 | Feb 26, 2026 |
|---|
| Image Classification | Tiny-ImageNet (train) | 35 | Apr 24, 2026 |
|---|
| Novel View Synthesis | DL3DV 140 (test) | 35 | Jul 7, 2026 |
|---|
| Node Classification | Minesweeper | 35 | Feb 26, 2026 |
|---|
| Migraine type classification | AoU (test) | 35 | Feb 26, 2026 |
|---|
| Concept Extraction Evaluation | 4 classification datasets average | 35 | Feb 26, 2026 |
|---|
| Node classification | Photo | 35 | Jun 25, 2026 |
|---|
| Sub-class Machine Unlearning | CIFAR-20 | 35 | Feb 26, 2026 |
|---|
| Counterfactual Outcome Prediction | MIMIC-III semi-synthetic (N=3000) (test) | 35 | Feb 26, 2026 |
|---|
| Counterfactual Outcome Prediction | MIMIC-III semi-synthetic (N=2000) (test) | 35 | Feb 26, 2026 |
|---|
| Counterfactual Outcome Prediction | MIMIC-III semi-synthetic (N=1000) (test) | 35 | Feb 26, 2026 |
|---|
| Portfolio Optimization | Noisy Portfolio Return Series | 35 | Feb 26, 2026 |
|---|