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 | AI2D | 402 | Jul 8, 2026 | ||
| Video Question Answering | MSVD-QA | 401 | Jun 23, 2026 | ||
| 3D Question Answering | ScanQA (val) |
| 391 |
| Jul 9, 2026 |
| Question Answering | SQuAD v1.1 (dev) | 380 | Apr 6, 2026 |
|---|
| Video Question Answering | MSRVTT-QA (test) | 376 | Mar 26, 2026 |
|---|
| Visual Question Answering | TextVQA (val) | 371 | Jun 24, 2026 |
|---|
| Science Question Answering | ScienceQA IMG | 357 | Jul 9, 2026 |
|---|
| Science Question Answering | ARC Challenge | 354 | May 12, 2026 |
|---|
| Boolean Question Answering | BoolQ | 350 | Apr 23, 2026 |
|---|
| Visual Question Answering | VQA v2 | 347 | Jun 18, 2026 |
|---|
| Question Answering | OBQA | 347 | May 28, 2026 |
|---|
| Science Question Answering | ScienceQA (SQA) | 338 | Jul 1, 2026 |
|---|
| Visual Question Answering | VQA 2.0 (test-dev) | 337 | Feb 26, 2026 |
|---|
| Multi-hop Question Answering | HotpotQA (test) | 334 | Jul 7, 2026 |
|---|
| Visual Question Answering | OK-VQA | 331 | Jun 26, 2026 |
|---|
| Visual Question Answering | RealworldQA | 327 | Jul 8, 2026 |
|---|
| Visual Question Answering | OK-VQA (test) | 327 | Mar 17, 2026 |
|---|
| Question Answering | BoolQ | 317 | Apr 21, 2026 |
|---|
| Document Visual Question Answering | DocVQA | 301 | May 21, 2026 |
|---|
| Multi-hop Question Answering | HotpotQA | 294 | Apr 23, 2026 |
|---|
| Document Visual Question Answering | DocVQA (test) | 292 | Jun 2, 2026 |
|---|
| Medical Visual Question Answering | SLAKE | 289 | Jul 1, 2026 |
|---|
| Video Question Answering | ActivityNet-QA (test) | 288 | Mar 20, 2026 |
|---|
| Visual Question Answering | OKVQA | 283 | Feb 27, 2026 |
|---|
| Question Answering | SciQ | 283 | Apr 8, 2026 |
|---|