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 |
|---|---|---|---|---|---|
| ECG Classification | PTB-XL | 31 | Jun 8, 2026 | ||
| Logical Reasoning | Countdown | 31 | Jun 19, 2026 | ||
| Multi-object 6D pose tracking | YCBMultiTrack Real-World | 31 | Apr 14, 2026 | ||
| Point Time Series Forecasting | ETTm1 | 31 | Jul 3, 2026 | ||
| Point Time Series Forecasting | ETTh1 | 31 | Jul 3, 2026 | ||
| Textures |
| 31 |
| Apr 30, 2026 |
| Image Quality Assessment | SRIQA | 31 | Jun 16, 2026 |
|---|
| Mathematical Reasoning | Mathematical Reasoning Suite (AIME24, AMC23, MATH, MIN., OLY.) | 31 | Apr 23, 2026 |
|---|
| Object Hallucination Evaluation | GQA Popular split | 31 | Jun 30, 2026 |
|---|
| Dimension Selection | SAUC | 31 | Jun 2, 2026 |
|---|
| Classification | Titanic | 31 | Apr 30, 2026 |
|---|
| Sales interaction performance | SalesLLM Chinese (ZH) 1.0 | 31 | Apr 10, 2026 |
|---|
| Reasoning | Overall Combined Benchmarks | 31 | May 19, 2026 |
|---|
| Recall-intensive retrieval | Recall-intensive retrieval tasks SWDE, SQUADE, FDA, Trivial QA, NQ, Drop | 31 | May 28, 2026 |
|---|
| Next POI Prediction | NYC | 31 | May 8, 2026 |
|---|
| Real-world Visual Question Answering | MME-RealWorld-Lite (MMERW) | 31 | Jul 7, 2026 |
|---|
| Text Retrieval | COCO 5k points (val) | 31 | Apr 8, 2026 |
|---|
| Classification | ImageNet standard (test) | 31 | Apr 8, 2026 |
|---|
| Multiclass classification | TALENT Multiclass (> 10 classes) Full (avg across datasets) | 31 | Apr 7, 2026 |
|---|
| Misclassification Detection | Cola | 31 | Apr 7, 2026 |
|---|
| Unsupervised Image Hashing | ImageNet 100 | 31 | Apr 7, 2026 |
|---|
| Spatial reasoning | ViewBench-Text 5–15% overlap | 31 | Apr 6, 2026 |
|---|
| Infrared Small Target Detection | NUDT-SIRST to NUAA-SIRST | 31 | Apr 3, 2026 |
|---|
| Infrared Small Target Detection | NUDT-SIRST to IRSTD-1K | 31 | Apr 3, 2026 |
|---|
| Mathematical Reasoning | MATH | 31 | Jun 16, 2026 |
|---|