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 |
|---|---|---|---|---|---|
| Question Answering | SciQ | 66 | Apr 29, 2026 | ||
| Question Answering | MedQUAD | 66 | Apr 29, 2026 | ||
| Multi-Hop Question Answering | HotpotQA | 66 | May 19, 2026 | ||
| Truthful Question Answering | TruthfulQA MC2 | 66 | Jun 8, 2026 | ||
| Visual Question Answering | VQA | 66 | May 19, 2026 | ||
| Question Answering |
| 2WikiMQA |
| 66 |
| Jun 4, 2026 |
| Visual Question Answering (Multiple-choice) | VQA 1.0 (test-dev) | 66 | Feb 26, 2026 |
|---|
| Question Answering | GPQA Diamond | 65 | Jun 5, 2026 |
|---|
| Medical Question Answering | HeadQA | 65 | Jun 16, 2026 |
|---|
| Medical Question Answering | PubMedQA | 65 | May 14, 2026 |
|---|
| Question Answering | TriviaQA | 65 | Jun 1, 2026 |
|---|
| Multi-Hop Question Answering | Multi-Hop QA (HotpotQA, 2Wiki, Musique, Bamboogle) (test) | 65 | Jun 11, 2026 |
|---|
| Medical Visual Question Answering | VQA-RAD (test) | 65 | Jun 12, 2026 |
|---|
| Video Question Answering | ActivityNet-QA zero-shot (test) | 65 | Jun 23, 2026 |
|---|
| Video Question Answering | MSRVTT-QA zero-shot (test) | 65 | Jun 23, 2026 |
|---|
| Multilingual Question Answering | TydiQA | 65 | Mar 12, 2026 |
|---|
| Visual Question Answering | VizWiz (test-dev) | 65 | Feb 27, 2026 |
|---|
| Question Answering | GPQA (test) | 65 | May 14, 2026 |
|---|
| Video Question Answering | RAVEN-QA Hard Queries | 64 | Jun 25, 2026 |
|---|
| Video Question Answering | RAVEN-QA Simple Queries | 64 | Jun 25, 2026 |
|---|
| Question Answering | NQ | 64 | May 12, 2026 |
|---|
| Question Answering | CoQA | 64 | May 27, 2026 |
|---|
| Question Answering | WebQA | 64 | May 27, 2026 |
|---|
| Question Answering | FreebaseQA | 64 | May 27, 2026 |
|---|
| Science Question Answering | ScienceQA | 64 | Mar 10, 2026 |
|---|