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 | qasper | 61 | Feb 27, 2026 | ||
| Question Answering | TruthfulQA | 61 | Mar 26, 2026 | ||
| OCR-based Visual Question Answering | OCR-VQA | 61 | Mar 5, 2026 | ||
| Visual Question Answering | VQA text | 61 | Apr 13, 2026 | ||
| Visual Question Answering | InfoSeek (Full) | 61 | May 6, 2026 | ||
| Multimodal Question Answering |
| MMBench CN |
| 61 |
| Jul 3, 2026 |
| Video Question Answering | VideoMME (test) | 61 | May 14, 2026 |
|---|
| Multimodal Question Answering | ScienceQA | 61 | Jun 1, 2026 |
|---|
| Multiple Choice Video Question Answering | EgoSchema | 61 | Feb 26, 2026 |
|---|
| Video Question Answering | MSRVTT-MC | 61 | Feb 26, 2026 |
|---|
| Visual Question Answering | CLEVR (test) | 61 | Feb 26, 2026 |
|---|
| Commonsense Question Answering | CSQA | 61 | May 19, 2026 |
|---|
| Visual Question Answering | HRBench-4K | 61 | May 21, 2026 |
|---|
| Visual Question Answering | PhD-icc | 60 | Jun 17, 2026 |
|---|
| Visual Question Answering | Conflict-VQA | 60 | Jun 17, 2026 |
|---|
| Question Answering under PIA attack | Bio | 60 | May 22, 2026 |
|---|
| Question Answering | TQA | 60 | May 22, 2026 |
|---|
| Science Question Answering | GPQA main (test) | 60 | Apr 14, 2026 |
|---|
| Single-Hop Question Answering | NQ | 60 | May 19, 2026 |
|---|
| Question Answering | NQ (Natural Questions) (test) | 60 | Feb 26, 2026 |
|---|
| Question Answering | RQA (test) | 60 | Feb 26, 2026 |
|---|
| Visual Question Answering | ScienceQA (SQA) | 60 | Jun 4, 2026 |
|---|
| Science Question Answering | ARC Challenge (test) | 60 | Jul 3, 2026 |
|---|
| Single-hop Question Answering | TriviaQA (test) | 60 | Jul 7, 2026 |
|---|
| Question Answering | ARC-e (test) | 60 | Jun 30, 2026 |
|---|