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 |
|---|---|---|---|---|---|
| Multilingual text-centric visual question answering | MTVQA | 37 | Apr 15, 2026 | ||
| Visual Question Answering | ScienceVQA | 37 | Jun 12, 2026 | ||
| Visual Question Answering | IR-VQA 9,720-sample (test) | 36 | Jul 8, 2026 | ||
| Question Answering | 2WikiMultihopQA | 36 | Jul 2, 2026 | ||
| Question Answering | MuSiQue | 36 | Jul 2, 2026 |
| Question Answering | HotpotQA | 36 | Jul 2, 2026 |
|---|
| Multihop Question Answering | 2WikiMultihopQA | 36 | Jul 2, 2026 |
|---|
| Multihop Question Answering | MuSiQue | 36 | Jul 2, 2026 |
|---|
| Multihop Question Answering | HotpotQA | 36 | Jul 2, 2026 |
|---|
| Question Answering | LoCoMo | 36 | Jun 23, 2026 |
|---|
| Knowledge-intensive Question Answering | CRAG | 36 | Jun 11, 2026 |
|---|
| Knowledge-conflict Question Answering | TriviaQA CF-RAG | 36 | Jun 5, 2026 |
|---|
| Knowledge-conflict Question Answering | PopQA CF-RAG | 36 | Jun 5, 2026 |
|---|
| Knowledge-conflict Question Answering | NQ Swap | 36 | Jun 5, 2026 |
|---|
| Question Answering | LongBench V1 | 36 | Jun 4, 2026 |
|---|
| Question Answering | ATE-Bench Q&A suite (Q1–Q12) | 36 | Jun 1, 2026 |
|---|
| Question Answering | ARC Challenge | 36 | May 28, 2026 |
|---|
| Question Answering | ARC Easy | 36 | May 28, 2026 |
|---|
| Truthful Question Answering | TruthfulQA | 36 | May 28, 2026 |
|---|
| Question Answering | AmbigQA | 36 | May 26, 2026 |
|---|
| Question Answering | Overall (NQ, PopQA, 2WikiQA, Musique, LOCOMO) (test) | 36 | May 12, 2026 |
|---|
| Conversation Question Answering | LOCOMO (test) | 36 | May 12, 2026 |
|---|
| Simple Question Answering | PopQA (test) | 36 | May 12, 2026 |
|---|
| Simple Question Answering | NQ* (test) | 36 | May 12, 2026 |
|---|
| Science Question Answering | GPQA-Diamond Science N=198 | 36 | May 8, 2026 |
|---|