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 |
|---|---|---|---|---|---|
| Offline Reinforcement Learning | MuJoCo Walker2d | 64 | May 26, 2026 | ||
| Offline Reinforcement Learning | MuJoCo Ant | 64 | May 26, 2026 | ||
| High-resolution image generation | Aesthetic-4K | 64 | May 22, 2026 | ||
| Theory of Mind | BigToM | 64 | Jun 11, 2026 | ||
| Adversarial Attack | Mini-ImageNet | 64 | May 21, 2026 | ||
| Modular Addition |
| Modular Addition (test) |
| 64 |
| May 11, 2026 |
| Visual Object Tracking | TrackingNet | 64 | Jul 3, 2026 |
|---|
| Medical Sycophancy Resistance | Medical Sycophancy | 64 | Apr 28, 2026 |
|---|
| Trajectory Prediction | HighD | 64 | Apr 21, 2026 |
|---|
| Backdoor Defense | CIFAR-10 | 64 | Apr 14, 2026 |
|---|
| Far Out-of-Distribution Detection | iNaturalist | 64 | Apr 14, 2026 |
|---|
| Image Captioning | COCO | 64 | Jun 15, 2026 |
|---|
| Traveling Thief Problem with Time Windows | TTPTW Benchmark | 64 | Apr 10, 2026 |
|---|
| 3D Object Detection | OPV2V 13 (test) | 64 | Apr 3, 2026 |
|---|
| Option Hedging | 317 shorter prediction horizons | 64 | Apr 2, 2026 |
|---|
| Option hedging | 317 longer prediction horizons (out-of-sample) | 64 | Apr 2, 2026 |
|---|
| Classification | Prostate_GE | 64 | May 6, 2026 |
|---|
| Clustering | STL-10 | 64 | Jun 5, 2026 |
|---|
| Multi-view reconstruction | CO3D v2 | 64 | Mar 27, 2026 |
|---|
| Multi-view reconstruction | DTU | 64 | Mar 27, 2026 |
|---|
| Hallucination Evaluation | CHAIR MSCOCO | 64 | Mar 26, 2026 |
|---|
| Question Answering | NQ | 64 | May 12, 2026 |
|---|
| Adversarial Attack | Heat Exchanger simulation dataset (test) | 64 | Mar 25, 2026 |
|---|
| Depth Super-Resolution | Lu (test) | 64 | May 12, 2026 |
|---|
| Few-shot 3D Semantic Segmentation | S3DIS (S0) | 64 | Jul 1, 2026 |
|---|