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 |
|---|---|---|---|---|---|
| Science Question Answering | GPQA Diamond | 84 | Jun 11, 2026 | ||
| Multiple Choice Question Answering | ArabCulture 1.0 (test) | 84 | Feb 26, 2026 | ||
| Confidence Calibration | MACE (test) | 84 | Feb 26, 2026 | ||
| Model Calibration | MACE | 84 | Feb 26, 2026 | ||
| Mathematical Problem Solving | AIME 25 |
| 84 |
| Jun 23, 2026 |
| Spatial Reasoning | MindCube (tiny) | 84 | Jul 7, 2026 |
|---|
| Question Answering | MuSiQue | 84 | Feb 26, 2026 |
|---|
| Visual Question Answering | Enc-VQA (test) | 84 | Mar 6, 2026 |
|---|
| Mathematical Reasoning | AIME 24 | 84 | Feb 26, 2026 |
|---|
| Image Classification Calibration | CIFAR10 | 84 | Apr 10, 2026 |
|---|
| Object Hallucination Evaluation | POPE Adversarial offline | 84 | Feb 26, 2026 |
|---|
| Object Hallucination Evaluation | POPE Popular offline | 84 | Feb 26, 2026 |
|---|
| Object Hallucination Evaluation | POPE Random offline | 84 | Feb 26, 2026 |
|---|
| Multi-Hop Knowledge Graph Question Answering | CWQ | 84 | Jul 8, 2026 |
|---|
| Multi-modal Question Answering | MMBench | 84 | May 26, 2026 |
|---|
| Node Classification | Citeseer original (test) | 84 | Feb 26, 2026 |
|---|
| Node Classification | Cora ML original (test) | 84 | Feb 26, 2026 |
|---|
| Safety Evaluation | Harmfulness Evaluation Sequences | 84 | Feb 26, 2026 |
|---|
| Document-Oriented Visual Question Answering | DocVQA | 84 | Apr 21, 2026 |
|---|
| Hallucination Detection | HELM Passage Level v1.0 (test) | 84 | Feb 26, 2026 |
|---|
| Hallucination Detection | HELM Sentence Level v1.0 (test) | 84 | Feb 26, 2026 |
|---|
| Arithmetic Reasoning | SVAMP (test) | 84 | Jun 26, 2026 |
|---|
| Few-shot Text Classification | 26 few-shot tasks Random -> Random transfer setting (test) | 84 | Feb 26, 2026 |
|---|
| Few-shot Text Classification | 26 few-shot tasks Non-Class -> Class transfer setting (test) | 84 | Feb 26, 2026 |
|---|
| Few-shot Text Classification | 26 few-shot tasks Class -> Non-Class transfer setting (test) | 84 | Feb 26, 2026 |
|---|