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 |
|---|---|---|---|---|---|
| Question Answering | Bio (test) | 105 | Feb 26, 2026 | ||
| Question Answering | ARC Challenge | 105 | Jun 2, 2026 | ||
| Few-Shot Segmentation | Multiple Datasets | 105 | Feb 26, 2026 | ||
| Multi-label scene classification | AID-ML (test) | 105 | Feb 26, 2026 | ||
| Multi-label scene classification | UCMerced | 105 | Feb 26, 2026 | ||
| Image Generation | LSUN Bedroom |
| 105 |
| Mar 25, 2026 |
| Prompt Injection Prevention | Alpaca-Farm | 105 | May 28, 2026 |
|---|
| Image Classification | ImageNet-32 down-sampled (test) | 105 | Feb 26, 2026 |
|---|
| Semantic Segmentation | Pascal VOC (Original set) | 105 | Feb 26, 2026 |
|---|
| Low-Light Image Enhancement | LOL Syn v2 (test) | 105 | Jul 7, 2026 |
|---|
| Clustering | ImageNet Dogs | 105 | May 14, 2026 |
|---|
| Vision-Language Tracking | OTB 99 | 105 | Jun 30, 2026 |
|---|
| Offline Reinforcement Learning | D4RL Medium HalfCheetah | 105 | May 11, 2026 |
|---|
| transductive dynamic link prediction | Social Evo. | 105 | Jul 7, 2026 |
|---|
| transductive dynamic link prediction | 105 | Jul 7, 2026 |
|---|
| Speech Recognition | Librispeech other (test) | 105 | Mar 27, 2026 |
|---|
| Dialogue State Tracking | MultiWOZ 2.1 (test) | 105 | Apr 15, 2026 |
|---|
| Backdoor Defense | AgNews | 105 | Mar 18, 2026 |
|---|
| Image Classification | ImageNet Domain Generalization (Source: ImageNet, Targets: ImageNetV2, ImageNet-Sketch, ImageNet-A, ImageNet-R) (test) | 105 | May 13, 2026 |
|---|
| Scene Text Recognition | IC13, IC15, IIIT, SVT, SVTP, CUTE80 Average of 6 benchmarks (test) | 105 | Feb 27, 2026 |
|---|
| Text-to-Image Retrieval | Flickr30K-CN | 105 | May 11, 2026 |
|---|
| Semantic Segmentation | BDD100K | 105 | Jul 9, 2026 |
|---|
| Anomaly Detection | MVTec | 105 | May 29, 2026 |
|---|
| Image Classification | ImageNet-C (val) | 105 | May 11, 2026 |
|---|
| 3D Object Detection | Waymo Open Dataset (test) | 105 | Feb 27, 2026 |
|---|