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 Retrieval | ImageNet @1000 (val) | 39 | Feb 26, 2026 | ||
| Image Retrieval | CIFAR-10 @1000 (test) | 39 | Feb 26, 2026 | ||
| Spatial Reasoning | VSI-Bench tiny | 39 | May 27, 2026 | ||
| Image Classification | Tiny-ImageNet | 39 | Mar 16, 2026 | ||
| General Video Understanding | MVBench Overall | 39 | Jun 18, 2026 | ||
| iCubWorld |
| 39 |
| Feb 26, 2026 |
| Few-Shot Class-Incremental Learning | CORe50 | 39 | Feb 26, 2026 |
|---|
| RGB-T Salient Object Detection | VT1000 (test) | 39 | Mar 16, 2026 |
|---|
| RGB-T Salient Object Detection | VT5000 (test) | 39 | Mar 16, 2026 |
|---|
| RGB-T Salient Object Detection | VT821 (test) | 39 | Mar 16, 2026 |
|---|
| Hallucination Assessment | HallusionBench | 39 | Apr 23, 2026 |
|---|
| Reasoning Video Object Segmentation | ReasonVOS (test) | 39 | Mar 31, 2026 |
|---|
| Surgical workflow recognition | M2CAI 2016 | 39 | Mar 24, 2026 |
|---|
| Spatial Reasoning | SITE | 39 | Mar 4, 2026 |
|---|
| Multimodal Understanding | Aggregate LLaVA 1.5 Suite | 39 | Jul 9, 2026 |
|---|
| Mobile GUI automation | AndroidLab | 39 | Jun 11, 2026 |
|---|
| Language Modeling | Enron Dataset | 39 | Feb 26, 2026 |
|---|
| Logical Reasoning | ReClor | 39 | Mar 19, 2026 |
|---|
| Text classification | WIPO | 39 | Feb 26, 2026 |
|---|
| Text classification | CLV | 39 | Feb 26, 2026 |
|---|
| Generative Question Answering | Bolmo Evaluation Suite GenQA 7B | 39 | Apr 7, 2026 |
|---|
| Arithmetic Reasoning | MATH | 39 | May 11, 2026 |
|---|
| Calibration | TriviaQA | 39 | Jun 1, 2026 |
|---|
| Language Modeling | 1BW | 39 | May 15, 2026 |
|---|
| Dialogue Segmentation | TIAGE | 39 | Jun 1, 2026 |
|---|