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 |
|---|---|---|---|---|---|
| Surface Normal Prediction | NYU Forget set v2 (train) | 30 | May 20, 2026 | ||
| Depth Estimation | NYU Forget set v2 (train) | 30 | May 20, 2026 | ||
| Semantic Segmentation | NYUv2 Forget set (train) | 30 | May 20, 2026 | ||
| Mathematics | GSM8K | 30 | Jun 30, 2026 | ||
| Tool-use gating | When2Call | 30 | May 20, 2026 | ||
| Knowledge Base Question Answering |
| CWQ |
| 30 |
| Jun 2, 2026 |
| Zero-shot Classification | Evaluation Suite (ARC-e, ARC-c, PIQA, HellaS., WinoG., BoolQ) Zero-shot (test) | 30 | May 19, 2026 |
|---|
| Fine-grained Image Hashing | Stanford Dogs (test) | 30 | May 19, 2026 |
|---|
| Fine-grained Image Hashing | Stanford Dogs | 30 | May 19, 2026 |
|---|
| Fine-grained Image Hashing | CUB200 2011 (test) | 30 | May 19, 2026 |
|---|
| Fine-grained Image Hashing | CUB200 2011 | 30 | May 19, 2026 |
|---|
| Factuality Evaluation | HaluEval Sum (500 items) | 30 | May 19, 2026 |
|---|
| Factuality Evaluation | HaluEval QA (500 items) | 30 | May 19, 2026 |
|---|
| Infrared Small Target Detection | IRDST | 30 | Jun 16, 2026 |
|---|
| Binary classification | clinical breast ultrasound dataset | 30 | May 19, 2026 |
|---|
| Image Classification | Image Classification Datasets (val) | 30 | May 19, 2026 |
|---|
| Natural Language Understanding | GLUE (test) | 30 | May 19, 2026 |
|---|
| Violation Detection | PolicyGuardBench | 30 | May 20, 2026 |
|---|
| Traffic Imputation (Sensor-kriging) | METR-LA | 30 | May 19, 2026 |
|---|
| Traffic Imputation (Sensor-kriging) | PEMS-BAY | 30 | May 19, 2026 |
|---|
| Traffic Imputation (Block-MAR) | METR-LA | 30 | May 19, 2026 |
|---|
| Traffic Imputation (Block-MAR) | PEMS-BAY | 30 | May 19, 2026 |
|---|
| Traffic Imputation (Cell-MAR) | METR-LA | 30 | May 19, 2026 |
|---|
| Traffic Imputation (Cell-MAR) | PEMS-BAY | 30 | May 19, 2026 |
|---|
| Image Classification | Fashion-MNIST | 30 | Jun 1, 2026 |
|---|