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 HalfCheetah Friction shift | 32 | May 26, 2026 | ||
| Scientific Reasoning | AI2-ARC Scientific | 32 | May 26, 2026 | ||
| Image-text grounding | Flickr30K | 32 | May 26, 2026 | ||
| Image-text grounding | COCO | 32 | May 26, 2026 | ||
| Image-text retrieval | ImageNet-C | 32 | May 26, 2026 | ||
| CIFAR-10-C |
| 32 |
| May 26, 2026 |
| AI-generated image detection | Ojha Diffusion Benchmark 1.0 (test) | 32 | Jun 25, 2026 |
|---|
| Sparse Decode Performance | 128K Context irregular sparse decode | 32 | May 26, 2026 |
|---|
| Skin Lesion Classification | ISIC Asymmetric Noise 2019 | 32 | May 22, 2026 |
|---|
| Skin Lesion Classification | ISIC Symmetric Noise 2019 | 32 | May 22, 2026 |
|---|
| Dishonesty Evaluation | Insecure code (test) | 32 | May 21, 2026 |
|---|
| Dishonesty Evaluation | Mistake medical (test) | 32 | May 21, 2026 |
|---|
| Trojan Detection | CelebA | 32 | May 21, 2026 |
|---|
| Trojan Detection | SVHN | 32 | May 21, 2026 |
|---|
| Multi-modal Understanding | MMBench | 32 | Jul 9, 2026 |
|---|
| Matrix Estimation | Symmetric Noise (test) | 32 | May 21, 2026 |
|---|
| Matrix Estimation | Pairflip Noise (test) | 32 | May 21, 2026 |
|---|
| Recommendation | Yelp | 32 | May 21, 2026 |
|---|
| Recommendation | MovieLens | 32 | May 21, 2026 |
|---|
| Recommendation | Adressa | 32 | May 21, 2026 |
|---|
| Piecewise-stationary low-rank bandit | Synthetic (d, r)-grid | 32 | May 21, 2026 |
|---|
| Long Video Understanding | LVOmniVideo | 32 | May 20, 2026 |
|---|
| Audio-Visual Dialogue | Daily-Omni | 32 | May 20, 2026 |
|---|
| Audio-Visual Reasoning | WorldSense | 32 | May 20, 2026 |
|---|
| GUI Grounding | MMBench GUI | 32 | Jun 30, 2026 |
|---|