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 | DuQuant PIQA, ARC-e, ARC-c, BoolQ, HellaS, WinoG | 44 | Jun 11, 2026 | ||
| Visual Question Answering | TextVQA | 44 | Jun 26, 2026 | ||
| Multiple-choice Question Answering | GPQA | 44 | Apr 23, 2026 | ||
| Multi-hop Question Answering | 2WikiMultiHopQA (val) | 44 | May 12, 2026 | ||
| Document Question Answering | Qasper |
| 44 |
| Mar 12, 2026 |
| Visual Question Answering | VQAv2 (test-std) | 44 | May 7, 2026 |
|---|
| Question Answering | ARC Easy | 44 | Feb 26, 2026 |
|---|
| Video Question Answering | NextQA MC | 44 | Apr 21, 2026 |
|---|
| Visual Question Answering | SlideBench-VQA TCGA | 44 | Mar 4, 2026 |
|---|
| Knowledge Base Question Answering | CWQ (test) | 44 | Jun 2, 2026 |
|---|
| Open-domain Question Answering | Natural Questions (NQ) (test) | 44 | Jun 11, 2026 |
|---|
| Visual Question Answer | VQA 1.0 (test-dev) | 44 | Feb 26, 2026 |
|---|
| Question Answering | Question Answering | 43 | Jun 23, 2026 |
|---|
| Multiple Choice Question Answering | Arc-Easy v1 (test) | 43 | Jun 12, 2026 |
|---|
| Question Answering | SearchQA | 43 | Jun 19, 2026 |
|---|
| Question Answering | TruthfulQA | 43 | May 15, 2026 |
|---|
| Medical Question Answering | MedQA US | 43 | May 19, 2026 |
|---|
| Science Question Answering | ARC-C | 43 | Jun 1, 2026 |
|---|
| Graph Question Answering | ExplaGraphs | 43 | Jun 5, 2026 |
|---|
| Medical Question Answering | DDXPlus | 43 | Mar 11, 2026 |
|---|
| Question Answering | MultiExpertQA All Base and Fine-tuned (FT) | 43 | Feb 26, 2026 |
|---|
| Visual Question Answering | Chest X-ray VQA (test) | 43 | Feb 26, 2026 |
|---|
| Single-hop Question Answering | PopQA (test) | 43 | Jul 7, 2026 |
|---|
| Visual Question Answering | WSI-VQA | 43 | Jun 9, 2026 |
|---|
| Audio Question Answering | MUSIC-AVQA 1.0 (test) | 43 | Feb 26, 2026 |
|---|