Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2443 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Conditional Code Generation | Conala | 15 | Mar 25, 2026 | ||
| Patient Simulation | Patient Simulation Profile Modeling Dataset | 15 | Mar 25, 2026 | ||
| No-Reference Image Quality Assessment | CSIQ 1.0 (test) | 15 | Mar 25, 2026 | ||
| No-Reference Image Quality Assessment | LIVEW 1.0 (test) | 15 | Mar 25, 2026 | ||
| No-Reference Image Quality Assessment | PIPAL 1.0 (test) | 15 | Mar 25, 2026 | ||
| No-Reference Image Quality Assessment | KADID 1.0 (test) | 15 | Mar 25, 2026 | ||
| No-Reference Image Quality Assessment | KonIQ-10K 1.0 (test) | 15 | Mar 25, 2026 | ||
| Membership Inference Attack | ImageNet | 15 | Apr 27, 2026 | ||
| Scene Classification | Taskonomy (val) | 15 | Mar 25, 2026 | ||
| Euclidean Depth Estimation | Taskonomy (val) | 15 | Mar 25, 2026 | ||
| 3D Keypoints | Taskonomy (val) | 15 | Mar 25, 2026 | ||
| Semantic Segmentation | Taskonomy (val) | 15 | Mar 25, 2026 | ||
| Surface Normals | Taskonomy (val) | 15 | Mar 25, 2026 | ||
| Reshading | Taskonomy (val) | 15 | Mar 25, 2026 | ||
| 2D Edges | Taskonomy (val) | 15 | Mar 25, 2026 | ||
| Information Retrieval | 18 datasets (BEIR, LoTTE, etc.) | 15 | Mar 25, 2026 | ||
| Survival Analysis | TCGA cohort | 15 | Mar 24, 2026 | ||
| Multi-object representation | ComCo | 15 | Mar 24, 2026 | ||
| Salient Object Detection | SSD 68 (test) | 15 | Mar 24, 2026 | ||
| Object Detection | FLIR v2 | 15 | May 12, 2026 | ||
| Multivariate Time Series Forecasting | Weather horizon 720 | 15 | Apr 21, 2026 | ||
| Attribution | ALCE Average | 15 | Mar 24, 2026 | ||
| Attribution | QAMPARI | 15 | Mar 24, 2026 | ||
| Attribution | ELI5 | 15 | Mar 24, 2026 | ||
| Attribution | ASQA | 15 | Mar 24, 2026 |