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 |
|---|---|---|---|---|---|
| Text-based Visual Question Answering | TextVQA (VQA^T) | 96 | Mar 24, 2026 | ||
| Question Answering | MedQA | 96 | Mar 4, 2026 | ||
| Audio-Visual Question Answering | MUSIC-AVQA 1.0 (test) | 96 | Feb 26, 2026 | ||
| Visual Question Answering | Vizwiz (val) | 96 | Jul 3, 2026 | ||
| Question Answering | ARC-E and PIQA (test) |
| 95 |
| Feb 26, 2026 |
| Question Answering | QuALITY (test) | 95 | Jun 26, 2026 |
|---|
| Visual Question Answering | ChartQA (test) | 95 | Jun 9, 2026 |
|---|
| Visual Question Answering | TextVQA | 94 | Mar 25, 2026 |
|---|
| Audio-Visual Question Answering | MUSIC-AVQA (test) | 94 | Jul 7, 2026 |
|---|
| Question Answering | HotPotQA | 93 | Jun 12, 2026 |
|---|
| Video Question Answering | NextQA | 92 | Jun 16, 2026 |
|---|
| Document Question Answering | DocVQA (test) | 92 | Apr 21, 2026 |
|---|
| Visual Question Answering | A-OKVQA (val) | 92 | Apr 21, 2026 |
|---|
| Commonsense Question Answering | CommonSenseQA | 92 | May 29, 2026 |
|---|
| Question Answering | IntraBench (test) | 91 | Apr 28, 2026 |
|---|
| Visual Question Answering | InfoVQA (val) | 91 | Apr 10, 2026 |
|---|
| Multiple Choice Question Answering | SciQ | 91 | May 25, 2026 |
|---|
| Question Answering | WQ (test) | 90 | Mar 23, 2026 |
|---|
| Question Answering | TQA (test) | 90 | Mar 23, 2026 |
|---|
| Question Answering | NQ (test) | 90 | Mar 23, 2026 |
|---|
| Question Answering | WQ | 90 | Mar 23, 2026 |
|---|
| Question Answering | TQA | 90 | Mar 23, 2026 |
|---|
| Question Answering | NQ | 90 | Mar 23, 2026 |
|---|
| Question Answering | WQ | 90 | Mar 23, 2026 |
|---|
| Question Answering | TQA | 90 | Mar 23, 2026 |
|---|