Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1524 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Sparse-View CT Reconstruction | AAPM | 21 | Feb 26, 2026 | ||
| Sparse-View CT Reconstruction | AAPM Coronal View (test) | 21 | Feb 26, 2026 | ||
| 3D Object Classification | ScanObjectNN PB_T50_RS v1 | 21 | Feb 26, 2026 | ||
| Single-hop Question Answering | SQuAD | 21 | Feb 26, 2026 | ||
| Semantic Segmentation | Pascal VOC Priority protocol 1/8 labeled ratio | 21 | Feb 26, 2026 | ||
| Semantic Segmentation | Pascal VOC Blended set (1/4) | 21 | Feb 26, 2026 | ||
| Semantic Segmentation | Pascal VOC Blended set (1/8) | 21 | Feb 26, 2026 | ||
| Semantic Segmentation | Pascal VOC Blended set (1/16) | 21 | Feb 26, 2026 | ||
| Novel View Rendering | Replica Of0 60 | 21 | Feb 26, 2026 | ||
| Targeted Data Extraction (TDE) Attack | URLs PII | 21 | Feb 27, 2026 | ||
| Targeted Data Extraction (TDE) Attack | phone PII | 21 | Feb 27, 2026 | ||
| Targeted Data Extraction (TDE) Attack | email PII | 21 | Feb 27, 2026 | ||
| Image Matching | HPatches (full) | 21 | Feb 26, 2026 | ||
| Style-Driven Image Generation | SDXL Complex Prompts 1.0 (test) | 21 | Feb 26, 2026 | ||
| Style-Driven Image Generation | SDXL Easy Prompts 1.0 (test) | 21 | Feb 26, 2026 | ||
| Medical Image Report Labeling | MIMIC-CXR (test) | 21 | Feb 26, 2026 | ||
| Chest X-ray Report Generation | MIMIC-CXR (test) | 21 | Feb 26, 2026 | ||
| Polyp Segmentation | Overall Combined Datasets | 21 | Feb 26, 2026 | ||
| Repository-level Method Body Completion | Defect4J | 21 | Feb 26, 2026 | ||
| Repo-level Method Body Completion | RAMBO's benchmark (test) | 21 | Feb 26, 2026 | ||
| Closed-loop Planning | Bench2Drive (test) | 21 | Feb 26, 2026 | ||
| Retrieval | Caltech-UCSD Birds-200 (CUB) 2011 (test) | 21 | Feb 26, 2026 | ||
| Mobile Automation | Android In The Wild (AITW) | 21 | Feb 26, 2026 | ||
| Image Registration | NLST (test) | 21 | Mar 4, 2026 | ||
| Online web agent task success rate | MobileMiniWob++ | 21 | May 13, 2026 |