Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2294 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Instance Segmentation | SUN-RGBD IS kv2 | 16 | Feb 26, 2026 | ||
| MIL Explanation | Pos-Neg (test) | 16 | Feb 26, 2026 | ||
| MIL Explanation | 4-Bags (test) | 16 | Feb 26, 2026 | ||
| Image Denoising | Set14 Gaussian σ=25 (test) | 16 | Feb 26, 2026 | ||
| Image Desnowing | CSD (test) | 16 | Feb 26, 2026 | ||
| Anomaly Localization | MPDD | 16 | Feb 26, 2026 | ||
| Sustainability Test | Fishery Sustainability default (test) | 16 | Feb 26, 2026 | ||
| Sustainability test | GOVSIM Pasture | 16 | Feb 26, 2026 | ||
| Sustainability Test | GOVSIM Pollution scenario, default experiment (test) | 16 | Feb 26, 2026 | ||
| Text Classification | UK Key Stage dataset | 16 | Feb 26, 2026 | ||
| Text-to-Video Generation | PickScore | 16 | Jun 29, 2026 | ||
| Multi-turn Psychological Counseling Dialogue Generation | CPsyCoun | 16 | Feb 26, 2026 | ||
| Molecular Property Regression | ESOL (test) | 16 | Feb 26, 2026 | ||
| 3D Multi-person Pose Estimation | MVOR 23 (test) | 16 | Feb 26, 2026 | ||
| Dialogue Generation | Anthropic-HH (test) | 16 | Feb 26, 2026 | ||
| Action Retrieval | NTU-120 (x-setup) | 16 | Feb 26, 2026 | ||
| Action Retrieval | NTU 120 (x-sub) | 16 | Feb 26, 2026 | ||
| 3D Human Pose and Shape Estimation | EMDB1 24 joints (test) | 16 | Feb 26, 2026 | ||
| Adversarial Detection | PGD perturbations (val) | 16 | Feb 26, 2026 | ||
| Out-of-Distribution Detection | iNaturalist (val) | 16 | Feb 26, 2026 | ||
| Shape Classification | ScanObjectNN OBJ-ONLY | 16 | Jun 11, 2026 | ||
| Point Cloud Reconstruction | DTU (evaluation) | 16 | Feb 26, 2026 | ||
| Visual Question Answering | INST-IT Bench Image | 16 | Feb 26, 2026 | ||
| Multitask Language Understanding | ArabicMMLU | 16 | Feb 26, 2026 | ||
| Science Question Answering | ARC | 16 | Feb 26, 2026 |