Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2289 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Anomaly Classification | MVTec 4 (test) | 16 | May 27, 2026 | ||
| Camera Pose Estimation | ScanNet 0079 | 16 | Feb 26, 2026 | ||
| Depth Estimation | ScanNet Individual Scenes | 16 | Feb 26, 2026 | ||
| Image Classification | CLIP Zero-shot Evaluation Suite (10 datasets) | 16 | Feb 26, 2026 | ||
| 3D Point Tracking | TAPVid-3D (minival) | 16 | Feb 26, 2026 | ||
| Online Video Understanding | OVBench 1.0 (test) | 16 | Feb 26, 2026 | ||
| Backdoor Detection | Tiny ImageNet (test) | 16 | Feb 26, 2026 | ||
| Test-Time Adaptation | Office-Home | 16 | May 1, 2026 | ||
| Image Classification | tiered-ImageNet (test) | 16 | Feb 26, 2026 | ||
| Person Re-identification | CARGO A ↔ A | 16 | May 15, 2026 | ||
| Object Detection | SIM10k to Cityscapes (val) | 16 | Feb 26, 2026 | ||
| Goal Conditioned Visual Navigation | RECON | 16 | Mar 6, 2026 | ||
| Global Pose Estimation | MotionPRO | 16 | Jun 26, 2026 | ||
| Pair-wise comparison | EvalBias | 16 | Feb 26, 2026 | ||
| Pair-wise comparison | JudgeBench | 16 | Feb 26, 2026 | ||
| Pair-wise comparison | MTBench Human | 16 | Feb 26, 2026 | ||
| Pair-wise comparison | HelpSteer2 | 16 | Feb 26, 2026 | ||
| Semantic Segmentation | PASCAL VOC 2012 V21 (val) | 16 | Feb 26, 2026 | ||
| Novel View Synthesis | NRHints (test) | 16 | Feb 26, 2026 | ||
| Full-body motion generation | GORP (Real MC) | 16 | Feb 26, 2026 | ||
| Motion generation from hand-tracking signal | GORP (Real HT) | 16 | Feb 26, 2026 | ||
| Visual Question Answering | ViQuAE | 16 | Mar 6, 2026 | ||
| Image Reconstruction | FaceScrub (val) | 16 | Feb 26, 2026 | ||
| Image Classification | FaceScrub (val) | 16 | Feb 26, 2026 | ||
| Image Classification and Reconstruction Defense | CIFAR100 (val test) | 16 | Feb 26, 2026 |