Research
Benchmarks for “question answering”
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
9,723 benchmarksPage 226 of 389
Search results
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Question Answering | DROP 2048 tokens | 8 | May 21, 2026 | ||
| Question Answering | Natural Questions (NQ) 2048 tokens | 8 | May 21, 2026 | ||
| Question Answering | TriviaQA (TQA) 2048 tokens | 8 | May 21, 2026 | ||
| Question Answering | SQuAD 2048 tokens | 8 | May 21, 2026 | ||
| Question Answering | PubMedQA | 8 | May 21, 2026 | ||
| Table Question Answering | FeTaQA (test) | 8 | May 21, 2026 | ||
| Question Answering | HotpotQA Full context | 8 | May 21, 2026 | ||
| Question Answering | HotpotQA Proxy context | 8 | May 21, 2026 | ||
| Visual Question Answering | GEOBench VLM | 8 | May 20, 2026 | ||
| Visual Question Answering | EarthVQA | 8 | May 20, 2026 | ||
| Question Answering | GPQA | 8 | May 20, 2026 | ||
| Visual Question Answering | RGBE-Chat | 8 | May 20, 2026 | ||
| Visual Question Answering | PEOD-Chat | 8 | May 20, 2026 | ||
| Question Answering | NQ (Held-out) | 8 | May 20, 2026 | ||
| Question Answering | TriviaQA (Held-out) | 8 | May 20, 2026 | ||
| Question Answering | ConflictBank (Held-out) | 8 | May 20, 2026 | ||
| Question Answering | ConflictQA (Held-out) | 8 | May 20, 2026 | ||
| Question Answering | ConFiQA-MC (Held-out) | 8 | May 20, 2026 | ||
| Question Answering | ConFiQA-MR (Held-out) | 8 | May 20, 2026 | ||
| Question Answering | ConFiQA-QA (Held-out) | 8 | May 20, 2026 | ||
| Graph Question Answering | GraphQA ExplaGraphs, SceneGraphs, WebQSP | 8 | May 19, 2026 | ||
| Question Answering | HealthQA | 8 | May 19, 2026 | ||
| Visual Question Answering | V* (test) | 8 | May 19, 2026 | ||
| Chart Question Answering | ChartQA Pro clean | 8 | May 18, 2026 | ||
| Tool-calling for Clinical Question Answering | AgentBench FHIR (val) | 8 | May 15, 2026 |