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 |
|---|---|---|---|---|---|
| Text Classification | SMS | 45 | Apr 13, 2026 | ||
| Image Classification | OfficeHome DomainBed suite (test) | 45 | Feb 27, 2026 | ||
| Video Question Answering | MVBench (test) | 45 | Apr 14, 2026 | ||
| Image-to-Text Retrieval | Flickr | 45 | Apr 15, 2026 | ||
| Mathematical Reasoning | SIMULEQ | 45 | Jun 9, 2026 | ||
| Personalized Image Generation |
| DreamBooth |
| 45 |
| Jul 1, 2026 |
| Gaussian Image Denoising | CBSD68 | 45 | Jun 18, 2026 |
|---|
| LGT Detection | MGTBench WritingPrompts | 45 | Feb 26, 2026 |
|---|
| Machine Generated Text Detection | MGT benchmark Reuters | 45 | Feb 26, 2026 |
|---|
| Long Video Understanding | Video-MME long 1.0 | 45 | Feb 26, 2026 |
|---|
| Denoising | BSD68 sigma=50 | 45 | Feb 26, 2026 |
|---|
| Denoising | BSD68 sigma=15 | 45 | Feb 26, 2026 |
|---|
| Image Classification | ImageNet-1K (val) | 45 | Feb 26, 2026 |
|---|
| Classification | steel | 45 | Feb 26, 2026 |
|---|
| Classification | biodeg | 45 | Feb 26, 2026 |
|---|
| Tabular Data Synthesis | steel | 45 | Feb 26, 2026 |
|---|
| Unconditional Image Generation | FFHQ unconditional 64x64 | 45 | Jun 9, 2026 |
|---|
| Machine Unlearning | TOFU 1.0 (Real Author) | 45 | May 19, 2026 |
|---|
| LLM-as-a-Judge | MTbench (test) | 45 | Feb 26, 2026 |
|---|
| Single Image Super-Resolution | Set5 x4 (test) | 45 | Jun 19, 2026 |
|---|
| Visual Question Answering | ScienceQA Image (test) | 45 | Feb 26, 2026 |
|---|
| Math Reasoning | MSVAMP (test) | 45 | Feb 26, 2026 |
|---|
| Image Classification | SIIM-ACR (test) | 45 | Feb 26, 2026 |
|---|
| Dynamic Scene Reconstruction | N3DV (test) | 45 | Jun 30, 2026 |
|---|
| Jailbreak Attack | AdvBench 150 Harmful Behaviors | 45 | Mar 12, 2026 |
|---|