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 |
|---|---|---|---|---|---|
| Causal Inference | IHDP connected regime | 72 | Apr 6, 2026 | ||
| CATE Estimation | IHDP connected regime | 72 | Apr 6, 2026 | ||
| Medical Reasoning | MedMCQA | 72 | Jun 30, 2026 | ||
| Fused CUDA kernel latency evaluation | normalized synthetic vectors | 72 | Mar 31, 2026 | ||
| Classification | SMK_CAN_187 | 72 | May 6, 2026 | ||
| Classification |
| ALLAML |
| 72 |
| May 6, 2026 |
| Image Classification | CIFAR10-0.5 (test) | 72 | Mar 31, 2026 |
|---|
| Image Classification | FMNIST 0.5 (test) | 72 | Mar 31, 2026 |
|---|
| Multi-source information fusion in RAG-based Web Q&A | EntityQuestions | 72 | Mar 26, 2026 |
|---|
| Time Series Forecasting | ETTm1 | 72 | Jun 19, 2026 |
|---|
| Long-context language modeling evaluation | RULER Context Length = 8K | 72 | Apr 8, 2026 |
|---|
| test allocation | Synchronous Activation Environment | 72 | Mar 23, 2026 |
|---|
| Spatial Allocation | International Territorial Level (ITL) Regions (train) | 72 | Mar 20, 2026 |
|---|
| Sequential Attribution | Multi-Agent Interaction Dataset | 72 | Mar 19, 2026 |
|---|
| Moral Alignment evaluation | Flames | 72 | Mar 17, 2026 |
|---|
| Multi-hop Question Answering | HotpotQA | 72 | Jun 5, 2026 |
|---|
| Camouflaged Object Detection | NC4K | 72 | Apr 21, 2026 |
|---|
| 5-way 5-shot Classification | CD-FSL (ISIC, EuroSAT, CropDisease, ChestX) (test) | 72 | May 29, 2026 |
|---|
| Review Feedback Generation | RMR-75K (val) | 72 | Mar 11, 2026 |
|---|
| Rotor-RPM estimation | Timestamped Quadcopter with Egomotion (TQE) (4-fold cross-val) | 72 | Mar 11, 2026 |
|---|
| Image Classification | CIFAR-10 0.2% fraction (test) | 72 | Mar 11, 2026 |
|---|
| Interactive Task Completion | ALFWorld | 72 | Jun 30, 2026 |
|---|
| Pre-training data detection | ArXivTection (test) | 72 | May 22, 2026 |
|---|
| Integer Nash Equilibrium search | Integer NEP instances with quadratic objectives | 72 | Mar 5, 2026 |
|---|
| Raw Image Reconstruction | S24 (test) | 72 | Mar 5, 2026 |
|---|