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 |
|---|---|---|---|---|---|
| Natural Language Inference | MNLI (mismatched) | 68 | Feb 26, 2026 | ||
| Image Classification | CIFAR-10-LT gamma=50 (test) | 68 | Jun 4, 2026 | ||
| Multiple Choice Question Answering | ARC-Easy (test) | 68 | Mar 4, 2026 | ||
| Semantic Textual Similarity | English STS | 68 | Feb 26, 2026 | ||
| Temporal Grounding | Charades-STA (test) |
| 68 |
| May 21, 2026 |
| Vision-and-Language Navigation | R2R (val seen) | 68 | Mar 31, 2026 |
|---|
| ObjectGoal Navigation | MP3D (val) | 68 | Feb 26, 2026 |
|---|
| Video-to-Text Retrieval | MSVD (test) | 68 | Apr 24, 2026 |
|---|
| Image Dehazing | Dense-Haze | 68 | Jun 18, 2026 |
|---|
| Image Classification | CIFAR-10 4000 labels | 68 | Feb 26, 2026 |
|---|
| Image Classification | ImageNet matched frequency V2 (test) | 68 | Jul 7, 2026 |
|---|
| Action Recognition | Toyota SmartHome (TSH) (CV1) | 68 | Mar 6, 2026 |
|---|
| Retrieval | HotpotQA | 68 | May 28, 2026 |
|---|
| Cardiac Segmentation | ACDC | 68 | Mar 24, 2026 |
|---|
| Image Classification | CIFAR-10 (test) | 68 | Feb 26, 2026 |
|---|
| Commonsense Question Answering | CosmosQA | 68 | May 11, 2026 |
|---|
| Anomaly Detection | ShanghaiTech | 68 | Feb 26, 2026 |
|---|
| Node Classification | ACM (test) | 68 | Jul 7, 2026 |
|---|
| Polyp Segmentation | CVC-ColonDB (test) | 68 | May 26, 2026 |
|---|
| Few-shot classification | CUB-200 2011 (test) | 68 | Apr 2, 2026 |
|---|
| Clustering | CIFAR-100-20 (test) | 68 | Feb 26, 2026 |
|---|
| Salient Object Detection | ECSSD 1,000 images (test) | 68 | May 26, 2026 |
|---|
| Action Recognition | Kinetics-600 (val) | 68 | Feb 26, 2026 |
|---|
| Model Calibration | CIFAR-10 | 68 | Apr 10, 2026 |
|---|
| Image Classification | Places205 (val) | 68 | Feb 26, 2026 |
|---|