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 |
|---|---|---|---|---|---|
| Image Classification | CIFAR-10N (Worst) | 89 | May 21, 2026 | ||
| Super-Resolution | Set5 | 89 | Mar 10, 2026 | ||
| Jailbreaking | AdvBench | 88 | Jun 26, 2026 | ||
| Communicative Success | WINE (test) | 88 | Jun 23, 2026 | ||
| Jailbreak Detection | AdvBench Llama2-7B | 88 | Jun 8, 2026 | ||
| Heuristic Search |
| Merge-and-shrink heuristic benchmark set |
| 88 |
| Jun 2, 2026 |
| Galaxy Cluster Mass Prediction | Galaxy Clusters | 88 | Jun 2, 2026 |
|---|
| Backdoor Attack | MNIST (test) | 88 | May 28, 2026 |
|---|
| Language Model Evaluation | Winogrande, ARC-C, ARC-E, Lambada, PIQA, Hellaswag, MMLU, IFEval, and GSM8K-CoT (Mixed standard 10-shot prompt) | 88 | May 13, 2026 |
|---|
| Speech Expressiveness Appropriateness Assessment | CEAEval 1.0 (test) | 88 | May 12, 2026 |
|---|
| Jailbreak Robustness | JailbreakBench | 88 | Jul 2, 2026 |
|---|
| Uncertainty Quantification | Aggregated Experimental Datasets (XSum, SamSum, CNN, WMT19, MedQUAD, TruthfulQA, CoQA, SciQ, TriviaQA, MMLU, GSM8k) (test) | 88 | Apr 29, 2026 |
|---|
| Commonsense Reasoning | CMQA | 88 | Apr 29, 2026 |
|---|
| Semantic Segmentation | Cityscapes | 88 | Jun 16, 2026 |
|---|
| Image Classification | Flowers102 | 88 | May 27, 2026 |
|---|
| Image Classification | Tiny-ImageNet | 88 | Apr 7, 2026 |
|---|
| 3D reconstruction | NRGBD | 88 | Jul 7, 2026 |
|---|
| Classification | GLI_85 | 88 | Jun 5, 2026 |
|---|
| 3D Question Answering | VSI-Bench | 88 | Jun 4, 2026 |
|---|
| Long-term forecasting | weather | 88 | Mar 17, 2026 |
|---|
| Sleep scoring | BOAS fixed (test) | 88 | Mar 12, 2026 |
|---|
| AI-Generated Video Detection | EA-Video seen (evaluation) | 88 | Feb 26, 2026 |
|---|
| Adversarial Attack Success Rate Assessment | AgentDojo | 88 | Apr 14, 2026 |
|---|
| Text-to-Image Generation | OneIG-ZH | 88 | Jun 26, 2026 |
|---|
| Scientific Reasoning | GPQA Diamond (test) | 88 | Jun 18, 2026 |
|---|