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 |
|---|---|---|---|---|---|
| Math Reasoning | Olympiad | 30 | Mar 16, 2026 | ||
| Long Video Question Answering | Video-MME | 30 | May 25, 2026 | ||
| Multi-entity reasoning grounding | ME-RSRG (test) | 30 | Mar 16, 2026 | ||
| Goal-reaching Planning | PointMaze Medium Long-Horizon (50 steps) | 30 | Mar 13, 2026 | ||
| Medical Question Answering | Polish Board Certification Examinations |
| 30 |
| Mar 13, 2026 |
| Large-scale Sparse Multi-objective Optimization | SMOP8 | 30 | Mar 13, 2026 |
|---|
| Large-scale Sparse Multi-objective Optimization | SMOP7 | 30 | Mar 13, 2026 |
|---|
| Large-scale Sparse Multi-objective Optimization | SMOP6 | 30 | Mar 13, 2026 |
|---|
| Large-scale Sparse Multi-objective Optimization | SMOP5 | 30 | Mar 13, 2026 |
|---|
| Large-scale Sparse Multi-objective Optimization | SMOP4 | 30 | Mar 13, 2026 |
|---|
| Large-scale Sparse Multi-objective Optimization | SMOP3 | 30 | Mar 13, 2026 |
|---|
| Anomaly Detection | Grid Loss D4 (test) | 30 | Mar 13, 2026 |
|---|
| Poisoning Attack | MuSiQue | 30 | Mar 13, 2026 |
|---|
| Poisoning Attack | Graph-Medical | 30 | Mar 13, 2026 |
|---|
| Poisoning Attack | Graph-Story | 30 | Mar 13, 2026 |
|---|
| Multi-view 3D Reconstruction | T&T (test) | 30 | Mar 13, 2026 |
|---|
| Multi-view 3D Reconstruction | ETH3D (test) | 30 | Mar 13, 2026 |
|---|
| Multi-view 3D Reconstruction | ScanNet++ (test) | 30 | Mar 13, 2026 |
|---|
| Text-to-image reward alignment | GenEval (test) | 30 | Mar 13, 2026 |
|---|
| Method ranking self-consistency | Combined benchmark M=120 questions | 30 | Mar 12, 2026 |
|---|
| Image Captioning Hallucination | MSCOCO 500 images (val) | 30 | Mar 12, 2026 |
|---|
| Structure-from-Motion | DTU | 30 | Mar 12, 2026 |
|---|
| Classification | ADHD-200 (test) | 30 | Jun 30, 2026 |
|---|
| PS | DexHand PS | 30 | Mar 12, 2026 |
|---|
| Machine Unlearning | TOFU (Forget01) | 30 | Jun 12, 2026 |
|---|