Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 323 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Novel View Synthesis | Synthetic-NeRF (test) | 56 | Jul 1, 2026 | ||
| Task-incremental learning | Split CIFAR-100 (test) | 56 | Jun 9, 2026 | ||
| Audio Retrieval | AudioCaps | 56 | May 19, 2026 | ||
| Image Classification | ImageNet-1k 1.0 (val) | 56 | Feb 26, 2026 | ||
| Novel View Synthesis | LLFF multi-scale (test) | 56 | Feb 26, 2026 | ||
| Multimodal classification | CASIA-SURF (test) | 56 | Feb 26, 2026 | ||
| Bias Defense | Average of four datasets (test) | 56 | Feb 26, 2026 | ||
| Monocular Depth Estimation | KITTI Eigen (test) | 56 | Apr 27, 2026 | ||
| Super-resolution | Urban100 official (test) | 56 | Feb 26, 2026 | ||
| Medical Report Generation | IU-Xray (test) | 56 | Mar 4, 2026 | ||
| 3D Semantic Segmentation | nuScenes (test) | 56 | May 11, 2026 | ||
| Capacitated Vehicle Routing Problem | CVRP N=100 10,000 instances (test) | 56 | Jun 30, 2026 | ||
| Node Classification | Chameleon h=0.23 (test) | 56 | Feb 26, 2026 | ||
| Graph Regression | ZINC Subset (test) | 56 | Feb 26, 2026 | ||
| Information Retrieval | MS MARCO | 56 | Jul 2, 2026 | ||
| Relation Extraction | Re-DocRED (test) | 56 | Jun 23, 2026 | ||
| Policy Search | Schedule(C, p) (test) | 56 | Feb 26, 2026 | ||
| Policy generation and execution | Keva (P, h) (test) | 56 | Feb 26, 2026 | ||
| 5-way 5-shot classification | miniImageNet (test) | 56 | Feb 26, 2026 | ||
| Unoriented Normal Estimation | PCPNet (test) | 56 | Feb 26, 2026 | ||
| Text-to-Video Retrieval | ActivityNet Captions | 56 | Feb 27, 2026 | ||
| Long-term action anticipation | 50 Salads | 56 | Feb 26, 2026 | ||
| Image Deraining | Rain100H (test) | 56 | Jun 30, 2026 | ||
| Semantic Segmentation | ADE20K 83 (val) | 56 | Feb 26, 2026 | ||
| Image Classification | CIFAR-100C Level 5 (test) | 56 | Apr 28, 2026 |