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 |
|---|---|---|---|---|---|
| Question Answering | ARC-C | 46 | Mar 23, 2026 | ||
| Visual Document Retrieval | MMLongBench | 46 | Mar 4, 2026 | ||
| Image Classification | MetaShift | 46 | Jun 4, 2026 | ||
| Travel Planning | TravelPlanner | 46 | May 4, 2026 | ||
| Color Gaussian Denoising | McMaster | 46 | May 26, 2026 | ||
| Color Gaussian Denoising | Kodak24 |
| 46 |
| May 26, 2026 |
| Leaderboard Evaluation | Open LLM Leaderboard 1 | 46 | Mar 4, 2026 |
|---|
| Math | GSM8K 5-shot | 46 | Mar 4, 2026 |
|---|
| Reasoning | MuSR 0-shot | 46 | Mar 4, 2026 |
|---|
| Knowledge | MMLU 5-shot | 46 | Mar 4, 2026 |
|---|
| Multi-hop Question Answering | FRAMES | 46 | Jun 18, 2026 |
|---|
| Medical Semantic Segmentation | SIIM Pneumothorax | 46 | Mar 19, 2026 |
|---|
| Image Classification | ImageNet | 46 | Mar 17, 2026 |
|---|
| Image Classification | ImageNet-S | 46 | Jun 8, 2026 |
|---|
| Accuracy prediction | NAS-Bench-101 1.0 | 46 | Feb 27, 2026 |
|---|
| Re-ranking | BEIR (test) | 46 | Apr 28, 2026 |
|---|
| Machine Translation | FLORES-200 xx→en | 46 | Apr 28, 2026 |
|---|
| Semantic Segmentation | Dv 58-class (val) | 46 | Feb 26, 2026 |
|---|
| Semantic Segmentation | Dv 19-class (val) | 46 | Feb 26, 2026 |
|---|
| Action Recognition | Kinetics 50C | 46 | Apr 23, 2026 |
|---|
| Classification | HAR | 46 | Jun 23, 2026 |
|---|
| Node classification | Chameleon | 46 | Jun 25, 2026 |
|---|
| Multi-task Question Answering | MMLU | 46 | Jun 18, 2026 |
|---|
| Unconditional molecule generation | GuacaMol | 46 | Jun 23, 2026 |
|---|
| Multi-Depot Vehicle Routing Problem | Cordeau's benchmark | 46 | Feb 26, 2026 |
|---|