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 |
|---|---|---|---|---|---|
| Short-term forecasting | M4 Quarterly | 166 | Jun 1, 2026 | ||
| Referring Video Object Segmentation | MeViS (val) | 166 | May 14, 2026 | ||
| L1 distance computation | High-dimensional WAN setting for L1 distance | 165 | Jun 16, 2026 | ||
| Robotic Manipulation | LIBERO | 165 | Jul 7, 2026 | ||
| Jailbreak Robustness |
| WildJailbreak |
| 165 |
| Jun 25, 2026 |
| Chart Question Answering | ChartQA | 165 | Jul 7, 2026 |
|---|
| Image Classification | ImageNet (val) | 165 | Jun 26, 2026 |
|---|
| Action Recognition | NTU-60 (xview) | 165 | Jun 30, 2026 |
|---|
| Image Generation | ImageNet 256 10k samples | 165 | Mar 17, 2026 |
|---|
| Heart Rate Estimation | PURE | 165 | Jul 1, 2026 |
|---|
| Video Action Recognition | UCF101 | 165 | May 28, 2026 |
|---|
| Image Classification | ImageNet Mobile Setting (test) | 165 | Feb 26, 2026 |
|---|
| Image Classification | Caltech (test) | 165 | Apr 9, 2026 |
|---|
| Generalized Referring Expression Segmentation | gRefCOCO (val) | 165 | May 29, 2026 |
|---|
| 3D Hand Reconstruction | FreiHAND (test) | 165 | Apr 23, 2026 |
|---|
| Referring Video Object Segmentation | Ref-DAVIS 17 | 165 | Jun 26, 2026 |
|---|
| Code Generation | MBPP | 165 | May 25, 2026 |
|---|
| Malware Detection | Androzoo | 164 | May 7, 2026 |
|---|
| Coding | HumanEval+ | 164 | Jun 9, 2026 |
|---|
| Scientific Reasoning | SciWorld | 164 | Feb 26, 2026 |
|---|
| GUI Grounding | OSWorld-G | 164 | Jul 1, 2026 |
|---|
| Visual Grounding | RefCOCO (TestB) | 164 | Jul 3, 2026 |
|---|
| Text Classification | MR (test) | 164 | Jun 26, 2026 |
|---|
| Shape Part Segmentation | ShapeNet (test) | 164 | Apr 14, 2026 |
|---|
| Link Prediction | FB15K (test) | 164 | Feb 26, 2026 |
|---|