Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 765 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Question Answering | Natural Questions (NQ) | 32 | May 27, 2026 | ||
| Document Retrieval | DUDE | 32 | May 20, 2026 | ||
| Document Retrieval | VisualMRC | 32 | Apr 10, 2026 | ||
| Knowledge Integration Quality | NQ, TruthfulQA, WoW, HotpotQA, ELI5 Aggregate | 32 | Apr 10, 2026 | ||
| Multi-hop Question Answering | HotpotQA | 32 | Apr 10, 2026 | ||
| Knowledge-grounded Dialogue | Wizard of Wikipedia (WoW) | 32 | Apr 10, 2026 | ||
| Target Product Selection | Target Product Selection transfer to fine-tunes | 32 | Apr 10, 2026 | ||
| Web-based interaction | MiniWoB | 32 | May 21, 2026 | ||
| Image Classification | MNIST (test) | 32 | Jun 9, 2026 | ||
| Regression | ERICH | 32 | Apr 10, 2026 | ||
| Sentiment Analysis | SloESG-News 1.0 (test) | 32 | Apr 10, 2026 | ||
| Uncertainty Quantification | LongFact | 32 | Apr 10, 2026 | ||
| Uncertainty Quantification | BIO | 32 | Apr 10, 2026 | ||
| Audio-Grounded Character Role-playing | AudioRole-Demo | 32 | Apr 9, 2026 | ||
| Sequence reconstruction | MIMIC-III | 32 | Apr 9, 2026 | ||
| Sequence reconstruction | CoLA | 32 | Apr 9, 2026 | ||
| Interactive Decision Making | ScienceWorld Unseen | 32 | May 19, 2026 | ||
| Multi-agent pathfinding | random map | 32 | Apr 8, 2026 | ||
| Multi-agent pathfinding | den520d map | 32 | Apr 8, 2026 | ||
| Cross-Domain Recommendation | Food Kitchen | 32 | Apr 21, 2026 | ||
| Long-context language generation | GovReport | 32 | Jun 2, 2026 | ||
| Visual Question Answering | SEED-Bench | 32 | Jun 12, 2026 | ||
| Long-term Forecasting | Weather 10% few-shot | 32 | Apr 7, 2026 | ||
| Long-term Forecasting | Electricity 10% few-shot | 32 | Apr 7, 2026 | ||
| Long-term Forecasting | ETTm2 10% few-shot | 32 | Apr 7, 2026 |