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 |
|---|---|---|---|---|---|
| Face Verification | IJB-A | 38 | Feb 26, 2026 | ||
| Single Image Dehazing | Synthetic Images NRE | 38 | Feb 26, 2026 | ||
| Scene Text Recognition | IC 2003 (test) | 38 | Feb 26, 2026 | ||
| Face Anti-Spoofing | Replay-Attack (test) | 38 | Mar 4, 2026 | ||
| Object Detection | VOC 07+12 (test) | 38 | Feb 27, 2026 | ||
| Regression | UCI WINE (test) |
| 38 |
| Jun 2, 2026 |
| User-Generated Content Video Quality Assessment | LIVE-VQC original (test) | 38 | Feb 26, 2026 |
|---|
| Person Re-Identification | CUHK03-NP source: DukeMTMC-reID (test) | 38 | Mar 17, 2026 |
|---|
| Video Retrieval | ActivityNet-Captions (test) | 38 | Feb 26, 2026 |
|---|
| Machine Translation | FLORES xx→en (test) | 38 | Feb 26, 2026 |
|---|
| Hypopnea Detection | SHHS (test) | 38 | Feb 26, 2026 |
|---|
| Apnea Detection | SHHS (test) | 38 | Feb 26, 2026 |
|---|
| Code Summarization | CodeXGLUE | 38 | Feb 26, 2026 |
|---|
| Tool-use decision-making | MetaTool (test) | 38 | Feb 26, 2026 |
|---|
| Vulnerability Detection | PrimeVul (test) | 38 | Feb 26, 2026 |
|---|
| Instance Segmentation | OCHuman (test) | 38 | Feb 26, 2026 |
|---|
| Pose Estimation | MegaDepth 1500 (test) | 38 | Apr 8, 2026 |
|---|
| Continual Learning | Standard CL Benchmark | 38 | Feb 26, 2026 |
|---|
| Mathematical Reasoning | GSM8K and MATH | 38 | Jun 2, 2026 |
|---|
| Multimodal Sentiment Analysis | CH-SIMS V2 | 38 | Apr 21, 2026 |
|---|
| Video Frame Prediction | Kinetics-600 | 38 | Mar 13, 2026 |
|---|
| Mathematical Reasoning | MATH-500 | 37 | Jun 26, 2026 |
|---|
| Pulmonary nodule segmentation | Single-center external dataset (n=885) (test) | 37 | Jun 23, 2026 |
|---|
| Competitive Mathematical Reasoning | AMC 2023 | 37 | Jun 9, 2026 |
|---|
| Competitive Mathematical Reasoning | AIME 2024 | 37 | Jun 9, 2026 |
|---|