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 |
|---|---|---|---|---|---|
| Multi-Hop Question Answering | Multi-Hop QA Aggregate | 30 | Mar 19, 2026 | ||
| Multi-Hop Question Answering | Bamb | 30 | Mar 19, 2026 | ||
| Single-Hop Question Answering | Trivia | 30 | Mar 19, 2026 | ||
| Visual Question Answering | VQA 10,000 samples v2 (val) | 30 | Jun 4, 2026 | ||
| Long Video Question Answering | Video-MME |
| 30 |
| May 25, 2026 |
| Medical Question Answering | Polish Board Certification Examinations | 30 | Mar 13, 2026 |
|---|
| Document Question Answering | LongDocURL | 30 | Apr 13, 2026 |
|---|
| Visual Question Answering | GQA | 30 | Mar 4, 2026 |
|---|
| Visual Question Answering | TextVQA (test val) | 30 | Apr 14, 2026 |
|---|
| Multi-Hop Question Answering | HotpotQA | 30 | Mar 11, 2026 |
|---|
| Question Answering Task | ARC-C (test) | 30 | Jun 30, 2026 |
|---|
| Question Answering | PopQA | 30 | Mar 25, 2026 |
|---|
| Table Question Answering | HiTab | 30 | Feb 26, 2026 |
|---|
| Multi-hop Question Answering | MuSiQue (val) | 30 | Jul 8, 2026 |
|---|
| Question Answering | MuSiQuest-E 2022 (Full) | 30 | Feb 26, 2026 |
|---|
| Question Answering | QASPER-E 2021 (Full) | 30 | Feb 26, 2026 |
|---|
| Question Answering | HotpotQA-E 2018 (Full) | 30 | Feb 26, 2026 |
|---|
| Question Answering | TriviaQA 5shots | 30 | Feb 26, 2026 |
|---|
| Question Answering | HotpotQA | 30 | Feb 26, 2026 |
|---|
| Question Answering | ARC | 30 | Feb 26, 2026 |
|---|
| Multiple Choice Question Answering | OpenBookQA | 30 | Jun 29, 2026 |
|---|
| Question Answering | All QA Datasets Average | 30 | Apr 28, 2026 |
|---|
| General Question Answering | NQ (Natural Questions) in-domain (val/test) | 30 | Jun 9, 2026 |
|---|
| Clinical Question Answering | MedQA | 30 | Jul 3, 2026 |
|---|
| Multimodal Question Answering | MMBench EN | 30 | Jul 3, 2026 |
|---|