Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 787 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Grayscale image JPEG compression artifact removal | LIVE1 | 32 | Feb 26, 2026 | ||
| Video Surface Normal Estimation | Sintel | 32 | Jun 30, 2026 | ||
| Holistic Social Debiasing Assessment | Alignment and Bias Level Evaluation (ABLE) | 32 | Feb 26, 2026 | ||
| Zero-shot Image-Text Retrieval | Flickr | 32 | Jul 2, 2026 | ||
| Social Debiasing | FACET Out-of-Domain | 32 | Feb 26, 2026 | ||
| Social Debiasing | Fairface Out-of-Domain | 32 | Feb 26, 2026 | ||
| Social Debiasing | UTKFace In-Domain | 32 | Feb 26, 2026 | ||
| Anomaly Detection | MSL, PSM, SMAP, SMD, SWAT (test) | 32 | Apr 1, 2026 | ||
| Backdoor Attack Detection and Mitigation | CIFAR-10 | 32 | May 21, 2026 | ||
| Continual Learning | CIFAR-100 Si-Blurry (test) | 32 | Jun 9, 2026 | ||
| OOD Detection | CIFAR-10 | 32 | Apr 15, 2026 | ||
| Offline Reinforcement Learning | Hopper D4RL v2 (offline) | 32 | Feb 26, 2026 | ||
| Offline Reinforcement Learning | Walker2d D4RL v2 (offline) | 32 | Feb 26, 2026 | ||
| Offline Reinforcement Learning | Halfcheetah D4RL v2 (offline) | 32 | Feb 26, 2026 | ||
| Tabular Data Synthesis | texture | 32 | Feb 26, 2026 | ||
| Image Classification | ImageNet 1k | 32 | Feb 26, 2026 | ||
| 3D Object Detection | Place3D (clean) | 32 | Feb 26, 2026 | ||
| LiDAR Semantic Segmentation | Place3D Adverse | 32 | Feb 26, 2026 | ||
| Image Classification | COVID-CT | 32 | May 27, 2026 | ||
| Image Restoration | Urban100 | 32 | Feb 26, 2026 | ||
| Reasoning | CQA | 32 | May 28, 2026 | ||
| Knowledge Graph Completion (KGC) | CHI | 32 | Feb 26, 2026 | ||
| Relational Triplet Extraction (RTE) | CHI | 32 | Feb 26, 2026 | ||
| Knowledge Graph Completion (KGC) | NYC | 32 | Feb 26, 2026 | ||
| Relational Triplet Extraction (RTE) | NYC | 32 | Feb 26, 2026 |