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 |
|---|---|---|---|---|---|
| Spatial Reasoning | Visual Spatial Reasoning (VSR) | 48 | Feb 26, 2026 | ||
| Jailbreak | HarmBench Standard Behaviours (200 examples) | 48 | Feb 26, 2026 | ||
| Identity Protection | CelebA (test) | 48 | Feb 26, 2026 | ||
| Question Answering | MedMCQA (test) | 48 | Jun 4, 2026 | ||
| Continuous Sign Language Recognition | PHOENIX-2014T (test) |
| 48 |
| Mar 18, 2026 |
| Inference Latency | A100 GPU | 48 | Jun 9, 2026 |
|---|
| Tabular Data Synthesis | fourier | 48 | Feb 26, 2026 |
|---|
| Infrared-Visible Image Fusion | LLVIP (test) | 48 | Jun 16, 2026 |
|---|
| Machine Unlearning | TOFU 1.0 (Retain Set) | 48 | May 19, 2026 |
|---|
| Point Tracking | TAP-Vid Kinetics | 48 | Mar 27, 2026 |
|---|
| Classification | dry-bean (test) | 48 | May 11, 2026 |
|---|
| Prostate Segmentation | Promise12 | 48 | May 28, 2026 |
|---|
| Action Recognition | UCF101 | 48 | Mar 31, 2026 |
|---|
| Named Entity Recognition | MultiCoNER | 48 | Feb 26, 2026 |
|---|
| Text Classification | MIND | 48 | Apr 14, 2026 |
|---|
| Visual Object Tracking | UAV123 | 48 | May 28, 2026 |
|---|
| Multivariate long-term forecasting | ETTh1 T=96 (test) | 48 | Feb 26, 2026 |
|---|
| Semantic Segmentation | ACDC Snow | 48 | Jul 9, 2026 |
|---|
| Semantic Segmentation | ACDC (Rain) | 48 | Jun 2, 2026 |
|---|
| Image Inpainting | Places2 irregular mask (val) | 48 | Feb 26, 2026 |
|---|
| No-Reference Image Quality Assessment | LIVEFB | 48 | May 28, 2026 |
|---|
| Multimodal Classification | MVSA (test) | 48 | Feb 26, 2026 |
|---|
| Multimodal Classification | KS (test) | 48 | Feb 26, 2026 |
|---|
| Class-Incremental Learning | Food101-LT rho=100 (test) | 48 | Feb 26, 2026 |
|---|
| Class-Incremental Learning | ImageNet Subset-LT rho=100 (test) | 48 | Feb 26, 2026 |
|---|