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 |
|---|---|---|---|---|---|
| Knowledge Editing | MQuAKE CF-3K v2 | 33 | Jun 4, 2026 | ||
| Robust Image Classification | cMNIST (test) | 33 | Jun 23, 2026 | ||
| Feature Attribution | 33 | Jun 2, 2026 | |||
| Feature Attribution | SciFact | 33 | Jun 2, 2026 | ||
| Feature Attribution | Movie | 33 | Jun 2, 2026 | ||
| Feature Attribution | HateXplain |
| 33 |
| Jun 2, 2026 |
| Feature Attribution | FEVER | 33 | Jun 2, 2026 |
|---|
| Feature Attribution | BoolQ | 33 | Jun 2, 2026 |
|---|
| Personalization | Personal | 33 | Jun 2, 2026 |
|---|
| Distribution Regression | Simulated Gaussian Distribution | 33 | Jun 2, 2026 |
|---|
| Mathematical Reasoning | HARDMath2 | 33 | Jun 1, 2026 |
|---|
| Nudity unlearning | I2P | 33 | Jul 1, 2026 |
|---|
| Multiple Choice Question Answering | HellaSwag | 33 | May 29, 2026 |
|---|
| Multiple Choice Question Answering | ARC Challenge | 33 | May 29, 2026 |
|---|
| Continual Learning | TRACE LLM-CL | 33 | May 28, 2026 |
|---|
| Multimodal Reasoning | MMMU-Pro | 33 | Jun 23, 2026 |
|---|
| Multi-task Language Understanding | MMLU | 33 | Jun 19, 2026 |
|---|
| Camouflaged Object Detection | NC4K | 33 | May 26, 2026 |
|---|
| Temporal Link Prediction | CollegeMsg (Transductive) | 33 | May 26, 2026 |
|---|
| Temporal Link Prediction | Enron (Transductive) | 33 | May 26, 2026 |
|---|
| Temporal Link Prediction | Wikipedia (Transductive) | 33 | May 26, 2026 |
|---|
| Active Learning | Multiple Datasets (test) | 33 | May 26, 2026 |
|---|
| Active Learning | Multiple Datasets (val) | 33 | May 26, 2026 |
|---|
| Regression | Mean across regression datasets (test) | 33 | May 26, 2026 |
|---|
| Regression | Mean across regression datasets (val) | 33 | May 26, 2026 |
|---|