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 |
|---|---|---|---|---|---|
| Document Parsing | OmniDocBench Real5 | 46 | Jun 23, 2026 | ||
| Science Question Answering | GPQA | 46 | Apr 7, 2026 | ||
| Mathematical Problem Solving | AIME 2025 | 46 | May 11, 2026 | ||
| ECG Classification | PTB-XL (test) | 46 | May 26, 2026 | ||
| Image-Text Retrieval | DCI long-text | 46 | Jul 2, 2026 |
| Robot Manipulation | MimicGen Stack Three D1 | 46 | Jun 19, 2026 |
|---|
| Image-to-Video Generation | VBench | 46 | Jul 7, 2026 |
|---|
| Reasoning | Bamboogle | 46 | Mar 24, 2026 |
|---|
| Algorithmic Reasoning | MATH | 46 | Mar 24, 2026 |
|---|
| Robot Manipulation | Libero | 46 | May 4, 2026 |
|---|
| Mathematical Reasoning | MINERVA | 46 | Jun 12, 2026 |
|---|
| Information Retrieval | LIMIT benchmark (test) | 46 | Mar 20, 2026 |
|---|
| Visual Mathematical Reasoning | MathVista | 46 | Apr 28, 2026 |
|---|
| Clustering | Music Analysis (test) | 46 | Mar 19, 2026 |
|---|
| Affine-invariant depth estimation | KITTI Outdoor | 46 | Mar 25, 2026 |
|---|
| Action Unit Detection | Aff-Wild2 (val) | 46 | Mar 16, 2026 |
|---|
| Safety Refusal | AdvBench | 46 | Mar 17, 2026 |
|---|
| Multilingual Language Proficiency | INCLUDE base-44 | 46 | Apr 14, 2026 |
|---|
| Stacking Three Blocks | Robomimic MimicGen Stack Three (D1) | 46 | Jun 19, 2026 |
|---|
| Question Answering | Average of 5 datasets | 46 | Apr 10, 2026 |
|---|
| Classification | australian | 46 | Apr 10, 2026 |
|---|
| Multiple Choice Question Answering | MC (test) | 46 | Mar 20, 2026 |
|---|
| Anomalous Sound Detection | DCASE 2020 (dev) | 46 | Mar 17, 2026 |
|---|
| Perception | MME-RealWorld Lite | 46 | May 5, 2026 |
|---|
| Heart Rate Estimation | MMPD (test) | 46 | Jun 11, 2026 |
|---|