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 |
|---|---|---|---|---|---|
| Mathematical Reasoning | AIME25 | 48 | Mar 4, 2026 | ||
| Mathematical Reasoning | AIME24 | 48 | Mar 4, 2026 | ||
| Instruction Following | Self-Instruct | 48 | Mar 5, 2026 | ||
| Eye Imaging Classification | FPRM | 48 | Mar 4, 2026 | ||
| Classification | FPRM | 48 | Mar 4, 2026 |
| Instance Segmentation | NWPU VHR-10 (test) | 48 | Mar 4, 2026 |
|---|
| Ship Instance Segmentation | HRSID-Inshore (test) | 48 | Mar 4, 2026 |
|---|
| Glioma Grading | TCGA GBM-LGG (3-fold val) | 48 | Mar 4, 2026 |
|---|
| Song identification | SONGS 0.0 | 48 | Feb 27, 2026 |
|---|
| Song Identification | Songs (rem = 0.2) | 48 | Feb 27, 2026 |
|---|
| Tracking | Strided EuRoC | 48 | Feb 27, 2026 |
|---|
| Medical Image Classification | RSNA | 48 | Mar 12, 2026 |
|---|
| Early Action Recognition | ActivityNet (test) | 48 | Feb 27, 2026 |
|---|
| Time-series Imputation | Time-series Datasets Average (test) | 48 | Feb 26, 2026 |
|---|
| Sequence Modeling | Industrial Dataset | 48 | Feb 26, 2026 |
|---|
| Optimization | Songs (rem=0.6) | 48 | Feb 27, 2026 |
|---|
| Song Identification | Songs (rem=0.4) | 48 | Feb 27, 2026 |
|---|
| Song Identification | SONGS (rem = 0.8) | 48 | Feb 27, 2026 |
|---|
| Finding optimal solutions | C-IGDP (test) | 48 | Feb 26, 2026 |
|---|
| Multi-task Language Understanding | MMLU-Redux | 48 | May 19, 2026 |
|---|
| Whole Slide Image Classification | BRACS | 48 | Jun 16, 2026 |
|---|
| Backward Visual Navigation (To Start) | HM3D | 48 | Feb 26, 2026 |
|---|
| Backward Visual Navigation (To Start) | Gibson | 48 | Feb 26, 2026 |
|---|
| Forward Visual Navigation (To End) | Gibson | 48 | Feb 26, 2026 |
|---|
| Machine Unlearning | ImageNette gas pump Class 7 (test) | 48 | Feb 27, 2026 |
|---|