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 |
|---|---|---|---|---|---|
| Molecular Property Prediction | ogbg-molbace | 30 | Feb 26, 2026 | ||
| Point-to-Point Geodesic Query | Mesh Models | 30 | Feb 26, 2026 | ||
| Medical Image Segmentation | ACDC 5% labeled (test) | 30 | Feb 26, 2026 | ||
| Image Classification | Tiny-ImageNet (test) | 30 | Apr 30, 2026 | ||
| Visual Question Answering | VQA v2 (dev) | 30 |
| Feb 26, 2026 |
| Multi-page Document Question Answering | MP-DocVQA (test) | 30 | Feb 26, 2026 |
|---|
| Object Detection | Objects365 v1 (val) | 30 | Feb 26, 2026 |
|---|
| CT Reconstruction | CBCT dataset | 30 | Feb 26, 2026 |
|---|
| Point Tracking | TAP-Vid Kinetics (test) | 30 | Feb 26, 2026 |
|---|
| 3D Action Recognition | NTU-120 (X-set) | 30 | Apr 7, 2026 |
|---|
| Optic Disc Segmentation | RIM-ONE r3 | 30 | Apr 24, 2026 |
|---|
| Image Retrieval | RSICD (test) | 30 | Feb 26, 2026 |
|---|
| Full-Reference Image Quality Assessment | TID 2013 (test) | 30 | Apr 23, 2026 |
|---|
| Full-Reference Image Quality Assessment | PIPAL | 30 | Feb 26, 2026 |
|---|
| Video Question Answering | MSVD (test) | 30 | Feb 27, 2026 |
|---|
| 3D Shape Generation | ShapeNet Airplane | 30 | Mar 20, 2026 |
|---|
| Image Classification | S-MNIST (test) | 30 | Mar 4, 2026 |
|---|
| Complex Query Answering | FB15k (test) | 30 | Feb 26, 2026 |
|---|
| Summarization | SAMSum | 30 | Feb 26, 2026 |
|---|
| Factual Consistency Evaluation | SAMSum | 30 | Feb 26, 2026 |
|---|
| Factual Consistency Evaluation | FRANK CNNDM | 30 | Feb 26, 2026 |
|---|
| Factual Consistency Evaluation | FRANK-XSum (FRK-X) | 30 | Feb 26, 2026 |
|---|
| Named Entity Recognition | SEC-filings (test) | 30 | Feb 26, 2026 |
|---|
| Empathetic Dialogue Generation | EMPATHETICDIALOGUES (test) | 30 | Apr 10, 2026 |
|---|
| Absolute 3D hand pose estimation | FreiHAND (test) | 30 | Feb 26, 2026 |
|---|