Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 227 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Few-shot Image Classification | Aggregated image datasets | 69 | Apr 20, 2026 | ||
| Agent Safety | ASSEBench | 69 | Jun 2, 2026 | ||
| Time Series Generation | ETTh | 69 | May 8, 2026 | ||
| Question Answering | ARC-c | 69 | Jun 26, 2026 | ||
| Question Answering | NQ | 69 | Jun 11, 2026 | ||
| User Engagement Prediction | Rel Stack | 69 | Apr 1, 2026 | ||
| Language Modeling | Penn Treebank | 69 | Mar 12, 2026 | ||
| Science Question Answering | GPQA | 69 | Apr 21, 2026 | ||
| Multimodal Understanding | MMMU | 69 | Apr 10, 2026 | ||
| Molecular Property Prediction (Regression) | ESOL | 69 | Jul 9, 2026 | ||
| Fine-grained Image Classification | CUB-200 2011 (test) | 69 | May 19, 2026 | ||
| Science Question Answering | GPQA | 69 | May 27, 2026 | ||
| Time Series Forecasting | FR | 69 | Mar 10, 2026 | ||
| Real-World Image Super-Resolution | DrealSR | 69 | Jun 16, 2026 | ||
| Image Generation | GenEval | 69 | May 21, 2026 | ||
| Point Map Estimation | 7-Scenes | 69 | May 29, 2026 | ||
| Transfer Attack | POPE (test) | 69 | Feb 26, 2026 | ||
| Text-to-SQL | EHRSQL | 69 | Jun 5, 2026 | ||
| Function Calling | BFCL Multi-Turn v3 | 69 | May 14, 2026 | ||
| Financial Reasoning | FinQA | 69 | May 26, 2026 | ||
| Grounded Video Question Answering | NExT-GQA | 69 | Jun 9, 2026 | ||
| 3D Question Answering | SQA3D | 69 | Apr 7, 2026 | ||
| Video Depth Estimation | Bonn 110 frames | 69 | Jul 3, 2026 | ||
| Traveling Salesman Problem | TSP-100 | 69 | Jun 2, 2026 | ||
| Affine-invariant depth estimation | ScanNet | 69 | Jun 30, 2026 |