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 |
|---|---|---|---|---|---|
| Visual Question Answering | VQAv2 | 226 | Jul 1, 2026 | ||
| Visual Question Answering | SimpleVQA | 225 | Jun 26, 2026 | ||
| Graduate-level Question Answering | GPQA |
| 224 |
| Jun 19, 2026 |
| Multiple-choice Question Answering | MMLU | 222 | Jun 29, 2026 |
|---|
| Visual Question Answering | GQA | 218 | Jun 24, 2026 |
|---|
| Multi-hop Question Answering | 2Wiki | 215 | May 8, 2026 |
|---|
| Question Answering | SQuAD 2.0 | 215 | May 8, 2026 |
|---|
| Multiple Choice Question Answering | HellaSwag | 212 | Jul 7, 2026 |
|---|
| Visual Question Answering | TextVQA | 210 | May 21, 2026 |
|---|
| Multi-hop Question Answering | Musique | 209 | Jun 29, 2026 |
|---|
| Knowledge Graph Question Answering | WebQSP | 209 | Jul 2, 2026 |
|---|
| Visual Question Answering | DocVQA | 205 | May 20, 2026 |
|---|
| Video Question Answering | NExT-QA (test) | 204 | Mar 17, 2026 |
|---|
| Visual Question Answering | GQA (test) | 204 | Jun 4, 2026 |
|---|
| Document Visual Question Answering | DocVQA | 203 | May 7, 2026 |
|---|
| Single-Hop Question Answering | PopQA | 200 | Jul 8, 2026 |
|---|
| Question Answering | QA Suite Zero-shot (PIQA, ARC-E, ARC-C, BoolQ, HellaSwag, WinoGrande) | 199 | Jun 11, 2026 |
|---|
| 3D Question Answering | SQA3D (test) | 197 | Jul 7, 2026 |
|---|
| Visual Question Answering | GQA | 196 | Apr 15, 2026 |
|---|
| Chart Question Answering | ChartQA (test) | 196 | Jun 16, 2026 |
|---|
| Video Question Answering | EgoSchema | 194 | Jun 30, 2026 |
|---|
| Visual Question Answering | VizWiz | 193 | Jul 7, 2026 |
|---|
| Visual Question Answering | GQA | 193 | Mar 30, 2026 |
|---|
| Medical Visual Question Answering | VQA-Med Open | 192 | Apr 6, 2026 |
|---|
| Science Question Answering | ScienceQA SQA-IMG | 186 | Apr 24, 2026 |
|---|