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 Question Answering | HELMET | 37 | May 11, 2026 | ||
| Text Question Answering | MuSiQue | 37 | May 11, 2026 | ||
| Text Question Answering | NQ | 37 | May 11, 2026 | ||
| Chart Question Answering | ChartQA | 37 | Jun 26, 2026 | ||
| Question Answering | TruthfulQA | 37 | Apr 21, 2026 | ||
| Knowledge Base Question Answering |
|---|
| T-REx WikiData (test) |
| 37 |
| May 25, 2026 |
| Visual Question Answering | OmniMedVQA BRIGHT Challenge | 37 | Jun 9, 2026 |
|---|
| Science Question Answering | ARC Challenge | 37 | Jun 11, 2026 |
|---|
| Truthful Question Answering | TruthfulQA | 37 | Jun 24, 2026 |
|---|
| Question Answering | ARC-E 0-shot | 37 | Apr 23, 2026 |
|---|
| Mathematical Visual Question Answering | MathVerse | 37 | Apr 10, 2026 |
|---|
| Visual Question Answering | VQA v2 | 37 | Feb 26, 2026 |
|---|
| Visual Question Answering | TextVQA | 37 | Feb 26, 2026 |
|---|
| Multi-hop Question Answering | Multi-Hop QA | 37 | Apr 24, 2026 |
|---|
| Visual Question Answering | countbenchqa | 37 | May 29, 2026 |
|---|
| Open-Domain Question Answering | WQ (test) | 37 | Feb 26, 2026 |
|---|
| Visual Question Answering | SlideBench-VQA BCNB | 37 | Mar 11, 2026 |
|---|
| Video Question Answering | IntentQA | 37 | Jul 2, 2026 |
|---|
| Visual Question Answering | VizWizQA | 37 | Mar 17, 2026 |
|---|
| Visual Question Answering | VQAT | 37 | Jul 1, 2026 |
|---|
| Long-form Question Answering with Citations | ASQA | 37 | Feb 26, 2026 |
|---|
| Question Answering | RelExt MRQA out-of-domain evaluation | 37 | Mar 12, 2026 |
|---|
| Question Answering | TextbookQA MRQA out-of-domain evaluation | 37 | Mar 12, 2026 |
|---|
| Question Answering | HotpotQA (test) | 37 | Mar 10, 2026 |
|---|
| Open-domain question answering | NaturalQ-Open (test) | 37 | Feb 26, 2026 |
|---|