Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2035 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Classification | m-so2sat (test) | 17 | May 21, 2026 | ||
| Molecular Energy Prediction | OMol25 (test) | 17 | Mar 9, 2026 | ||
| Scene Graph Generation | IndoorVG (test) | 17 | Jun 5, 2026 | ||
| Mobile UI Reasoning | AMEX | 17 | Mar 9, 2026 | ||
| Action Prediction | AITZ (test) | 17 | Mar 9, 2026 | ||
| Image Classification | Caltech-USCD Birds-200 (CUB) Proposed Split 2011 | 17 | Mar 9, 2026 | ||
| Temporal Action Segmentation | MCFS 22 | 17 | Mar 26, 2026 | ||
| Open-ended Generation | WildBench (test) | 17 | Mar 9, 2026 | ||
| Object Detection | LVIS zero-shot (mini val) | 17 | Jun 9, 2026 | ||
| Document and Chart Understanding | AI2D | 17 | Jun 30, 2026 | ||
| Robotic Manipulation | LIBERO Spatial | 17 | Apr 1, 2026 | ||
| Tumor analysis | TumorCoT 1.5M (test) | 17 | Mar 9, 2026 | ||
| Time Series Forecasting | Exchange rate (test) | 17 | Jun 2, 2026 | ||
| Multimodal Document Question Answering | DocBench | 17 | Mar 11, 2026 | ||
| Wildfire risk prediction | Wildfire Events OOD | 17 | Mar 9, 2026 | ||
| Object Detection | NYU Depth v2 (test) | 17 | Mar 9, 2026 | ||
| Knowledge-based Agent Reasoning | KARLBench 1.0 (test) | 17 | Mar 6, 2026 | ||
| Multi-step theorem prediction | FormalGeo7K (test) | 17 | Mar 6, 2026 | ||
| Anomalous Sound Detection | DCASE 2023 (eval) | 17 | Mar 6, 2026 | ||
| Anomalous Sound Detection | DCASE 2023 (dev) | 17 | Mar 6, 2026 | ||
| Retrieval | DVisRAG Dataset Real | 17 | Mar 6, 2026 | ||
| Retrieval | VisRAG Dataset | 17 | Mar 6, 2026 | ||
| Visual Question Answering | GAR-Bench-VQA | 17 | Mar 6, 2026 | ||
| Image Compression | Kodak 1 (test) | 17 | Mar 6, 2026 | ||
| 3D Semantic Segmentation | ScanNet | 17 | Mar 26, 2026 |