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 | PopQA | 158 | Jul 8, 2026 | ||
| Knowledge Graph Question Answering | CWQ (test) | 158 | Jun 29, 2026 | ||
| Visual Question Answering | VQA v2 (val) | 158 | May 26, 2026 | ||
| Question Answering | OpenBookQA | 157 | Jul 9, 2026 | ||
| Social Interaction Question Answering | SIQA |
| 157 |
| Jun 1, 2026 |
| Question Answering | SQuAD (test) | 156 | Jul 8, 2026 |
|---|
| Medical Question Answering | MedQA | 153 | Mar 31, 2026 |
|---|
| Question Answering | ARC (test) | 153 | May 12, 2026 |
|---|
| Multimodal Science Question Answering | ScienceQA IMG | 152 | Jun 2, 2026 |
|---|
| Visual Question Answering | GQA | 152 | Jun 16, 2026 |
|---|
| Visual Question Answering | LiveVQA | 151 | Jul 7, 2026 |
|---|
| Visual Question Answering | MMStar | 151 | Jul 7, 2026 |
|---|
| Multi-hop Question Answering | MuSiQue (test) | 151 | Jul 7, 2026 |
|---|
| Science Question Answering | ScienceQA SQA-I | 149 | Jul 1, 2026 |
|---|
| Visual Question Answering | VQA (test-dev) | 147 | Mar 18, 2026 |
|---|
| Single-hop Question Answering | TriviaQA | 147 | Jul 8, 2026 |
|---|
| Medical Question Answering | MedQA | 145 | Jun 25, 2026 |
|---|
| Knowledge Base Question Answering | WebQSP (test) | 145 | Jun 2, 2026 |
|---|
| Question Answering | PubMedQA | 145 | Feb 26, 2026 |
|---|
| Question Answering | NQ (test) | 143 | Jun 30, 2026 |
|---|
| Diagram Question Answering | AI2D (test) | 142 | Mar 5, 2026 |
|---|
| Visual Question Answering | VQA v2 (test) | 142 | Jun 16, 2026 |
|---|
| Text-based Visual Question Answering | TextVQA | 141 | Jun 26, 2026 |
|---|
| Table Question Answering | WikiTQ (test) | 140 | May 19, 2026 |
|---|
| Multiple Choice Question Answering | MMLU-Pro | 138 | Jun 4, 2026 |
|---|