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 |
|---|---|---|---|---|---|
| Medical Visual Question Answering | MMMU Health & Medicine (test) | 39 | Apr 14, 2026 | ||
| Multiple Choice Question Answering | MedQA | 39 | Mar 16, 2026 | ||
| Video Question Answering | PerceptionTest | 39 | Jul 7, 2026 | ||
| Multiple-Choice Question Answering | TruthfulQA MC1 | 39 | Apr 3, 2026 | ||
| Open-domain Question Answering | NQ (test) | 39 | May 29, 2026 |
| Open-domain question answering | SQUAD Open (test) | 39 | Feb 26, 2026 |
|---|
| Visual Question Answering | SimpleVQA | 38 | Jul 7, 2026 |
|---|
| Question Answering | ESGenius | 38 | Jun 11, 2026 |
|---|
| Medical Question Answering | MediQ offline (test) | 38 | Jun 9, 2026 |
|---|
| Clinical Question Answering | MedXpertQA Multimodal modality (offline) | 38 | Jun 9, 2026 |
|---|
| Clinical Question Answering | LiveClin Multimodal (offline) | 38 | Jun 9, 2026 |
|---|
| Clinical Question Answering | LiveMedBench (offline) | 38 | Jun 9, 2026 |
|---|
| Clinical Question Answering | HealthBench (offline) | 38 | Jun 9, 2026 |
|---|
| Clinical Question Answering | MedXpertQA Text modality (offline) | 38 | Jun 9, 2026 |
|---|
| Clinical Question Answering | LiveClin Text modality (offline) | 38 | Jun 9, 2026 |
|---|
| Question Answering | Molmo2-Moment (M2M) v1 (test) | 38 | May 25, 2026 |
|---|
| Question Answering | MultiFieldQA en | 38 | Apr 28, 2026 |
|---|
| Question Answering | NarrativeQA | 38 | Apr 28, 2026 |
|---|
| Question Answering | WMDP Biology | 38 | Apr 14, 2026 |
|---|
| Question Answering | WMDP Cyber QA | 38 | Apr 14, 2026 |
|---|
| Video Question Answering | Traffic-VQA (test) | 38 | Mar 12, 2026 |
|---|
| Visual Question Answering | VQA v2 (test val) | 38 | Jun 16, 2026 |
|---|
| Multi-modal Question Answering | MedXpertQA-MM | 38 | Apr 13, 2026 |
|---|
| Visual Question Answering | MME | 38 | Jun 11, 2026 |
|---|
| Long-context Question Answering | DetectiveQA-En | 38 | May 8, 2026 |
|---|