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 |
|---|---|---|---|---|---|
| Medical Image Segmentation | SCD (test) | 42 | Jun 2, 2026 | ||
| Natural Language Inference | CNLI | 42 | Jun 2, 2026 | ||
| Natural Language Inference | WANLI | 42 | Jun 2, 2026 | ||
| Toxicity Detection | Adv | 42 | Jun 2, 2026 | ||
| Sentiment Analysis | DynaSent | 42 | Jun 2, 2026 | ||
| Preference Prediction | Arena-Expert-5K, HelpSteer3, HH-RLHF, and UltraFeedback (held-out) |
| 42 |
| Jun 1, 2026 |
| Uncertainty Quantification | InfoSeek (val) | 42 | May 29, 2026 |
|---|
| Uncertainty Quantification | Encyclopedic VQA (EVQA) (test) | 42 | May 29, 2026 |
|---|
| Optimization modeling and solving | IndustryOR | 42 | Jun 26, 2026 |
|---|
| Multitask LLM Evaluation | Aggregated MMLU, GSM8K, HumanEval | 42 | May 29, 2026 |
|---|
| Code Generation | HumanEval | 42 | May 29, 2026 |
|---|
| Grade School Math Reasoning | GSM8K | 42 | May 29, 2026 |
|---|
| Massive Multitask Language Understanding | MMLU | 42 | May 29, 2026 |
|---|
| Unified Retrieval across Heterogeneous Knowledge Sources | OmniRetrieval Macro-averaged Text/SQL/SPARQL/Cypher 1.0 (test) | 42 | May 29, 2026 |
|---|
| Target Aspect Sentiment Detection | Rest16 | 42 | May 28, 2026 |
|---|
| Discriminative Hallucination Evaluation | AMBER (test) | 42 | Jul 7, 2026 |
|---|
| Image Classification | TinyImageNet | 42 | May 28, 2026 |
|---|
| Image Classification | CIFAR-10 | 42 | May 28, 2026 |
|---|
| Irregular Multivariate Time Series Forecasting | Human Activity (test) | 42 | May 28, 2026 |
|---|
| Irregular Multivariate Time Series Forecasting | PhysioNet (test) | 42 | May 28, 2026 |
|---|
| Irregular Multivariate Time Series Forecasting | MIMIC (test) | 42 | May 28, 2026 |
|---|
| 3D Geometry Estimation and Reconstruction | SpatialBench Average across settings | 42 | May 27, 2026 |
|---|
| 3D Geometry Estimation and Reconstruction | SpatialBench Medium | 42 | May 27, 2026 |
|---|
| 3D Geometry Estimation and Reconstruction | SpatialBench Sparse | 42 | May 27, 2026 |
|---|
| 3D Geometry Estimation and Reconstruction | SpatialBench Single Frame | 42 | May 27, 2026 |
|---|