Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1386 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Information Retrieval | Quora BEIR | 22 | May 26, 2026 | ||
| Information Retrieval | NFCorpus BEIR | 22 | Mar 20, 2026 | ||
| Information Retrieval | FEVER BEIR | 22 | Mar 20, 2026 | ||
| Multimodal Ranking | MMEB | 22 | Feb 26, 2026 | ||
| Recommendation | Amazon Sports | 22 | Apr 28, 2026 | ||
| Recommendation | Goodbooks-10k (test) | 22 | Feb 26, 2026 | ||
| Image Classification | CIFAR-100 | 22 | Feb 26, 2026 | ||
| Image Classification | CIFAR-10 | 22 | Feb 26, 2026 | ||
| Image Classification | Food101, DTD, Caltech101, Flowers102, and OxfordPets base-to-new generalization CLIP baseline | 22 | Feb 26, 2026 | ||
| 4D Generation | VBench | 22 | Jun 9, 2026 | ||
| AI-generated image detection | WIFR | 22 | May 21, 2026 | ||
| HR estimation | PURE (five-fold cross-validation) | 22 | Jun 4, 2026 | ||
| Multimodal Understanding | MMBench MMB EN | 22 | May 22, 2026 | ||
| Single Image Reflection Removal | Nature 20 (test) | 22 | Jul 1, 2026 | ||
| Single Image Reflection Removal | SIR2 454 (test) | 22 | Jul 1, 2026 | ||
| Spatial Reasoning | CV-Bench 2D | 22 | Mar 10, 2026 | ||
| Jailbreak attacks | MM-Safety | 22 | Jul 7, 2026 | ||
| Aerial Visual Grounding | AerialSense (test) | 22 | Feb 26, 2026 | ||
| Aerial Visual Question Answering | AerialVP | 22 | Feb 26, 2026 | ||
| Aerial Visual Reasoning | AerialVP | 22 | Feb 26, 2026 | ||
| Novel View Synthesis | DL3DV (evaluation) | 22 | Feb 26, 2026 | ||
| Motion Planning | nuScenes v1.0 (test) | 22 | Jul 7, 2026 | ||
| Oriented Object Detection | DOTA 1.0 (val) | 22 | May 6, 2026 | ||
| Semantic Segmentation | BCSS-WSSS (test) | 22 | Feb 26, 2026 | ||
| Comprehension | GUI-EDA 1.0 (test) | 22 | Feb 26, 2026 |