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 Generation | ImageNet 50k samples (test) | 35 | Mar 5, 2026 | ||
| Text-to-image generation | MSCOCO 30k samples 2014 (val) | 35 | Mar 5, 2026 | ||
| Inductive dynamic link prediction | UCI | 35 | Jun 4, 2026 | ||
| RAG Attack | MS-MARCO | 35 | Mar 5, 2026 | ||
| Object Hallucination | COCO captions 2014 (val) | 35 | Mar 5, 2026 |
| Face Recognition | CPLFW | 35 | Jun 1, 2026 |
|---|
| Egocentric Planning | Ego-Plan 2 | 35 | Jun 9, 2026 |
|---|
| Image Compression | Tecnick (test) | 35 | Jun 23, 2026 |
|---|
| Flexible Job Shop Scheduling | la Hurink benchmark | 35 | Mar 4, 2026 |
|---|
| MSI Completion | Feathers 256x256x31 (test) | 35 | Mar 4, 2026 |
|---|
| MSI Completion | Balloons 256x256x31 (test) | 35 | Mar 4, 2026 |
|---|
| MSI Completion | Beers 256x256x31 (test) | 35 | Mar 4, 2026 |
|---|
| MSI Completion | Flowers 256x256x31 (test) | 35 | Mar 4, 2026 |
|---|
| False Refusal Evaluation | ORB-H | 35 | Mar 4, 2026 |
|---|
| Satellite image generation | Git-Spatial 15k | 35 | Jul 1, 2026 |
|---|
| Satellite image generation | Git-Rand 15k | 35 | Jul 1, 2026 |
|---|
| Multi-Subject | GPQA | 35 | Mar 4, 2026 |
|---|
| Medical Visual Question Answering | SLAKE | 35 | Jun 8, 2026 |
|---|
| Targeted Attack Detection | Alpaca AddTarget Medium | 35 | Mar 4, 2026 |
|---|
| MRI Reconstruction | fastMRI knee | 35 | Jun 16, 2026 |
|---|
| Causal Discovery | child | 35 | May 27, 2026 |
|---|
| Denoising | Salinas (217 x 217 x 224) HSI (test) | 35 | Mar 4, 2026 |
|---|
| Denoising | Washington DC 256 x 256 x 191 HSI (test) | 35 | Mar 4, 2026 |
|---|
| Denoising | Toys 256 x 256 x 31 MSI (test) | 35 | Mar 4, 2026 |
|---|
| Tensor Completion | Carphone 144 x 176 x 100 | 35 | Mar 4, 2026 |
|---|