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 |
|---|---|---|---|---|---|
| Image Classification | Caltech101 | 84 | May 26, 2026 | ||
| PDE rollout prediction | diff-react PDEBench (test) | 84 | Mar 20, 2026 | ||
| Multi-view spatial reasoning | MINDCUBE Tiny | 84 | Jul 2, 2026 | ||
| Mathematical Reasoning | AMC | 84 | Jun 1, 2026 | ||
| Coding | HumanEval | 84 | Jun 15, 2026 | ||
| Open Medical-LLM leaderboard |
| 84 |
| Mar 16, 2026 |
| Unconditional Image Generation | FFHQ 64 x 64 | 84 | Jun 9, 2026 |
|---|
| User Clicks Prediction | Rel Avito | 84 | Apr 1, 2026 |
|---|
| Image Classification | BUSI | 84 | Jun 30, 2026 |
|---|
| Single Object Tracking | TrackingNet | 84 | Jun 24, 2026 |
|---|
| Image Editing | GEdit-Bench-EN (full) | 84 | May 8, 2026 |
|---|
| Open-loop planning | nuScenes v1.0-trainval (val) | 84 | Jun 11, 2026 |
|---|
| Time Series Forecasting | ETTm2 (5% train) | 84 | May 14, 2026 |
|---|
| Mathematical Reasoning | Countdown (test) | 84 | Jun 1, 2026 |
|---|
| Remaining Useful Life prediction | C-MAPSS FD003 | 84 | Jun 18, 2026 |
|---|
| Intrusion Detection | Edge-IIoTset | 84 | Feb 26, 2026 |
|---|
| Time Series Forecasting | NP | 84 | Mar 10, 2026 |
|---|
| Monte Carlo Integration | Example 2 | 84 | Feb 27, 2026 |
|---|
| Classification | CRC-KRAS TCGA cohort | 84 | Feb 26, 2026 |
|---|
| Open-loop planning | nuScenes v1.0 (test) | 84 | Jun 23, 2026 |
|---|
| Open Vocabulary Semantic Segmentation | COCO-Stuff | 84 | Jun 23, 2026 |
|---|
| Vectorized HD Map Construction | nuScenes v1.0-trainval (val) | 84 | Mar 23, 2026 |
|---|
| Video Understanding | LongVideoBench, MLVU, and VideoMME Aggregate | 84 | May 19, 2026 |
|---|
| Novel View Synthesis | DL3DV | 84 | Mar 31, 2026 |
|---|
| Multi-modal Video Understanding | MVBench | 84 | Jun 17, 2026 |
|---|