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 Quality Assessment | TID 2013 | 74 | Feb 26, 2026 | ||
| Question Answering | SQuAD (dev) | 74 | Feb 26, 2026 | ||
| Image Search | Flickr8K | 74 | Feb 26, 2026 | ||
| EEG Emotion Recognition | SEED | 74 | Jul 7, 2026 | ||
| Image Generation | ImageNet 128x128 |
| 74 |
| May 20, 2026 |
| Deepfake Detection | CDFv1, CDFv2, DFD, DFDCP, DFDC (test) | 74 | Mar 11, 2026 |
|---|
| Out-of-Distribution Detection | SSB hard | 74 | Apr 13, 2026 |
|---|
| Semantic Segmentation | NYU V2 | 74 | Feb 27, 2026 |
|---|
| General Capability | MMLU | 74 | May 13, 2026 |
|---|
| Anomaly Segmentation | RESC | 74 | Feb 26, 2026 |
|---|
| Question Answering | MMLU | 74 | Jun 2, 2026 |
|---|
| Multimodal Understanding | MMMU | 73 | Jun 30, 2026 |
|---|
| Math Reasoning | Minerva Math | 73 | Jun 23, 2026 |
|---|
| Federated Learning | Shakespeare (val) | 73 | May 1, 2026 |
|---|
| Human Activity Recognition | MM-Fi | 73 | May 12, 2026 |
|---|
| Moral Alignment Evaluation | Flames Benchmark | 73 | Mar 17, 2026 |
|---|
| Mathematical Reasoning | Olympiad | 73 | May 7, 2026 |
|---|
| Mathematical Reasoning | MATH (test) | 73 | Jun 24, 2026 |
|---|
| Long-term Time Series Forecasting | Electricity (test) | 73 | Jun 1, 2026 |
|---|
| Inductive dynamic link prediction | LastFM | 73 | Jul 7, 2026 |
|---|
| Code Generation | BigCodeBench Hard | 73 | Jun 18, 2026 |
|---|
| General Reasoning | Out-of-Distribution Performance Suite (ARC-c, GPQA*, MMLU-Pro) (test) | 73 | Jun 4, 2026 |
|---|
| Multi-Agent Path Finding (MAPF) | random 64x64-20 | 73 | Feb 26, 2026 |
|---|
| Mathematical Reasoning | GSM-Symbolic | 73 | Apr 6, 2026 |
|---|
| Spatio-temporal Forecasting | UrbanEV (test) | 73 | Feb 26, 2026 |
|---|