Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 659 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| 3D Domain Adaptation | PointDA-10 | 36 | Feb 27, 2026 | ||
| Image Classification | ImageIDC (val) | 36 | May 19, 2026 | ||
| Neural Architecture Search | HW-NAS-Bench (val) | 36 | Feb 26, 2026 | ||
| Semantic Segmentation | Poland dataset | 36 | Feb 26, 2026 | ||
| QR code scanning | 100 generated aesthetic QR codes 5 (test) | 36 | Feb 26, 2026 | ||
| Instruction-based Image Editing | InstructPE (test) | 36 | Feb 26, 2026 | ||
| Multivariate Time Series Classification | HandMovementDirection | 36 | May 4, 2026 | ||
| Text-to-Video Retrieval | DiDeMo (DDM) zero-shot | 36 | May 27, 2026 | ||
| RGB-D Salient Object Detection | LFSD (test) | 36 | Mar 24, 2026 | ||
| Medical Image Classification | COVIDx | 36 | Feb 27, 2026 | ||
| Code Generation | LeetCode Contest Benchmark | 36 | Mar 10, 2026 | ||
| Graph Classification | Molbbbp (scaffold) | 36 | May 4, 2026 | ||
| Diabetic Retinopathy Diagnosis | APTOS 2019 (Population Shift) | 36 | Feb 26, 2026 | ||
| Diabetic Retinopathy Diagnosis | EyePACS In-Domain | 36 | Feb 26, 2026 | ||
| Multi-task Generalization | Other tasks (test) | 36 | Feb 26, 2026 | ||
| Image Classification | ImageNet-D | 36 | Apr 2, 2026 | ||
| Fixel-based analysis | HCP 8 subjects (test) | 36 | Feb 26, 2026 | ||
| Action Recognition | NTU120 (cross-subject (CS)) | 36 | Feb 26, 2026 | ||
| Offline Reinforcement Learning | D4RL MuJoCo Hopper-mr v2 (medium-replay) | 36 | Mar 10, 2026 | ||
| Long-tail recognition | ImageNet-LT | 36 | Feb 26, 2026 | ||
| Learning to Defer | CIFAR100 (test) | 36 | May 1, 2026 | ||
| Novel View Synthesis | BungeeNeRF | 36 | Mar 19, 2026 | ||
| 3D Human Reconstruction | ZJU Mocap (test) | 36 | Apr 20, 2026 | ||
| Visual Question Answering | VQAv2 | 36 | Feb 26, 2026 | ||
| Classification | WHU-RS19 (test) | 36 | Jun 9, 2026 |