Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 693 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Multimodal Retrieval | Multi30k (test) | 35 | Feb 26, 2026 | ||
| Visual Localization | Cambridge Landmarks (test) | 35 | Feb 26, 2026 | ||
| Referring Video Segmentation | JHMDB Sentences (test) | 35 | Feb 26, 2026 | ||
| Image Classification | Office-Caltech (test) | 35 | Feb 26, 2026 | ||
| OOD detection | OOD Suite Average | 35 | Jun 17, 2026 | ||
| Stereo Matching | Middlebury v3 | 35 | Jun 30, 2026 | ||
| LiDAR Semantic Segmentation | SemanticKITTI sequences 11 to 21 (test) | 35 | Feb 26, 2026 | ||
| Image Classification | CIFAR-100 LT IF 50 (test) | 35 | Feb 26, 2026 | ||
| Image Generation | CIFAR-100 (full data) | 35 | Feb 26, 2026 | ||
| Image Generation | CIFAR-10 (10% data) | 35 | Feb 26, 2026 | ||
| Image Generation | CIFAR-10 (20% data) | 35 | Feb 26, 2026 | ||
| 4D Panoptic Segmentation | SemanticKITTI (val) | 35 | Feb 26, 2026 | ||
| Graph-level prediction | OGBG-MOLPCBA (test) | 35 | Feb 26, 2026 | ||
| Image-to-recipe retrieval | Recipe1M 1.0 (test) | 35 | Feb 26, 2026 | ||
| Image Classification | iNaturalist (test) | 35 | May 12, 2026 | ||
| Question Answering | MLQA (test) | 35 | Feb 26, 2026 | ||
| Node classification | PATTERN | 35 | Jun 26, 2026 | ||
| Out-of-Distribution Detection | CIFAR-10 Interp. | 35 | Feb 26, 2026 | ||
| Class Incremental Learning | ImageNet 100 (incremental) | 35 | Feb 26, 2026 | ||
| kNN Classification | Shuttle | 35 | May 13, 2026 | ||
| Few-shot classification | Omniglot 5-way 5-shot (test) | 35 | Feb 26, 2026 | ||
| Video Summarization | SumMe (test) | 35 | Feb 26, 2026 | ||
| Anomaly Detection | ImageNet (test) | 35 | Feb 26, 2026 | ||
| Video Prediction | KTH | 35 | Feb 26, 2026 | ||
| Image Generation | CIFAR-100 (test) | 35 | Feb 26, 2026 |