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 |
|---|---|---|---|---|---|
| Audio Watermarking | LJSpeech | 88 | Feb 26, 2026 | ||
| Graph Classification | Cora | 88 | May 26, 2026 | ||
| Remaining Useful Life prediction | C-MAPSS FD002 | 88 | Jun 18, 2026 | ||
| Image Generation | CIFAR-10 | 88 | Feb 26, 2026 | ||
| Deformable Image Registration | DIRLab 4DCT | 88 | Feb 26, 2026 | ||
| Time-series Classification |
| UCI-HAR |
| 88 |
| Jul 1, 2026 |
| Anomaly Detection | BraTS 2018 (test) | 88 | Feb 26, 2026 |
|---|
| Retrieval | THINGS-EEG 200-way zero-shot retrieval (Inter-Subject) | 88 | May 7, 2026 |
|---|
| OCR Visual Question Answering | TextVQA | 88 | Jun 23, 2026 |
|---|
| Vision-Language Understanding | MMBench | 88 | Jul 7, 2026 |
|---|
| Zero-shot Downstream Task Evaluation | ARC-c, ARC-e, WinoGrande, BoolQ, HellaSwag, OpenBookQA, PIQA, MMLU standard (test val) | 88 | Feb 26, 2026 |
|---|
| Language Modeling | WikiText2 2016 (test) | 88 | Feb 26, 2026 |
|---|
| Mathematical Reasoning | GSM8k Aug | 88 | Jul 1, 2026 |
|---|
| Visual Mathematical Reasoning | MathVista (testmini) | 88 | May 15, 2026 |
|---|
| 3D Reconstruction | Neural RGB-D (NRGBD) | 88 | Mar 19, 2026 |
|---|
| Tabular Data Synthesis Fidelity | fourier | 88 | Feb 26, 2026 |
|---|
| Tabular Data Synthesis Fidelity | protein | 88 | Feb 26, 2026 |
|---|
| Text Membership Inference Attack | LLaVA LLM Pre-training | 88 | Feb 26, 2026 |
|---|
| Graph Classification | OGBG-MOLHIV v1 (test) | 88 | Feb 26, 2026 |
|---|
| Multivariate long-term time series forecasting | Solar-Energy | 88 | Jun 29, 2026 |
|---|
| Automatic Speech Recognition | TED-LIUM3 (test) | 88 | Jun 11, 2026 |
|---|
| Camouflaged Object Detection | NC4K | 88 | May 18, 2026 |
|---|
| Conditional Image Generation | CIFAR-10 | 88 | May 29, 2026 |
|---|
| Future Link Prediction | MOOC (inductive) | 88 | Jul 7, 2026 |
|---|
| Federated Learning Classification | MNIST FedAvg 0.962 (test) | 88 | Feb 26, 2026 |
|---|