Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1469 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Graph classification | PubMed (test) | 21 | May 19, 2026 | ||
| Node Classification | ogbn-arxiv 5-shot | 21 | Jun 11, 2026 | ||
| Agentic Reasoning | ALFWorld (test) | 21 | Mar 27, 2026 | ||
| 3D Object Detection | OPV2V-H (test) | 21 | Mar 10, 2026 | ||
| Node classification | Books | 21 | May 14, 2026 | ||
| Tracking | Waymo | 21 | Jun 30, 2026 | ||
| Visual Tracking | VOT STB 2022 | 21 | Jul 3, 2026 | ||
| CT Reconstruction | Knee (test) | 21 | Mar 10, 2026 | ||
| CT Reconstruction | PENGWIN Pelvis (test) | 21 | Mar 10, 2026 | ||
| CT Reconstruction | PANORAMA Abdomen (test) | 21 | Mar 10, 2026 | ||
| CT Reconstruction | LUNA16 Chest (test) | 21 | Mar 10, 2026 | ||
| CT Reconstruction | ToothFairy Head (test) | 21 | Mar 10, 2026 | ||
| Sparse-view CT Reconstruction | Knee | 21 | Mar 10, 2026 | ||
| Sparse-view CT Reconstruction | LUNA16 Chest | 21 | Mar 10, 2026 | ||
| Full-class unlearning | Tiny ImageNet | 21 | Mar 10, 2026 | ||
| Relational Triple Classification | YAGO 39K | 21 | Mar 10, 2026 | ||
| Link Prediction | YAGO39K | 21 | Mar 10, 2026 | ||
| Zero-shot language understanding | Zero-shot Benchmarks | 21 | Jun 1, 2026 | ||
| Human Preference Prediction | HPD v3 | 21 | May 12, 2026 | ||
| Infrared-Visible Image Fusion | Infrared-Visible Fusion Missing-IR Modality (test) | 21 | Mar 10, 2026 | ||
| Super-resolution | DIV2K 1 (val) | 21 | May 5, 2026 | ||
| Retrieval | 2WikiMultiHopQA v1 (test) | 21 | Mar 10, 2026 | ||
| Retrieval | MuSiQue v1 (test) | 21 | Mar 10, 2026 | ||
| Retrieval | HotpotQA v1 (test) | 21 | Mar 10, 2026 | ||
| Chain-of-Thought Reasoning | Reasoning Dataset | 21 | Mar 10, 2026 |