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 |
|---|---|---|---|---|---|
| Mathematical Reasoning | GSM8k | 80 | Jun 9, 2026 | ||
| Translation Estimation | BcOT 1.0 (complex_movable_handheld) | 80 | Apr 13, 2026 | ||
| Orientation Estimation | BcOT complex_movable_handheld 1.0 | 80 | Apr 13, 2026 | ||
| Pose Estimation | BcOT complex_movable_handheld | 80 | Apr 13, 2026 | ||
| Silhouette-based Pose Estimation | BcOT 1.0 (test) |
| 80 |
| Apr 13, 2026 |
| RAG Performance Prediction | TriviaQA | 80 | Apr 10, 2026 |
|---|
| RAG Performance Prediction | HotpotQA | 80 | Apr 10, 2026 |
|---|
| RAG Performance Prediction | NQ-Open | 80 | Apr 10, 2026 |
|---|
| Recommendation Diversity | MovieLens | 80 | Apr 10, 2026 |
|---|
| Lipschitz constant estimation | Large-scale Feedforward Neural Networks Evaluation on random weights | 80 | Apr 9, 2026 |
|---|
| Cross-lingual Information Retrieval | Belebele | 80 | Apr 8, 2026 |
|---|
| Multimodal Model Evaluation | MME | 80 | Jun 9, 2026 |
|---|
| Question Answering | MuSiQue | 80 | May 27, 2026 |
|---|
| Heart Rate Estimation | MMPD | 80 | Jul 1, 2026 |
|---|
| Function Optimization | CEC 100D 2017 | 80 | Mar 31, 2026 |
|---|
| Image Classification | MNIST 0.5 (test) | 80 | Mar 31, 2026 |
|---|
| Instruction Following | DomainBench | 80 | Mar 26, 2026 |
|---|
| Time-series forecasting | ETTh2 | 80 | Jun 16, 2026 |
|---|
| Hallucination Detection | SciQ | 80 | Jun 12, 2026 |
|---|
| Anomaly Detection | MVTec-AD | 80 | Mar 20, 2026 |
|---|
| Commonsense Reasoning | Commonsense 8 Sub-Tasks | 80 | Jun 4, 2026 |
|---|
| Adversarial Attack | ImageNet (val) | 80 | Mar 16, 2026 |
|---|
| Sliced Wasserstein Distance Estimation | Banana-shaped target d=10 | 80 | Mar 11, 2026 |
|---|
| Geometric Accuracy | DTU (all points) | 80 | Mar 9, 2026 |
|---|
| dynamic link prediction | MOOC (transductive) | 80 | Jun 4, 2026 |
|---|