Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 820 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Misclassification Detection | CIFAR-10 | 31 | May 26, 2026 | ||
| Video Question Answering | iVQA (test) | 31 | Feb 27, 2026 | ||
| Open-set Unsupervised Video Domain Adaptation | Epic-Kitchens | 31 | Feb 26, 2026 | ||
| Word Similarity | SimLex-999 | 31 | Apr 14, 2026 | ||
| Category-level Object Pose Estimation | CAMERA25 | 31 | Jul 7, 2026 | ||
| Visual Place Recognition | Nordland (test) | 31 | Feb 26, 2026 | ||
| Traffic Forecasting | PEMS-BAY 60min horizon 12 | 31 | May 8, 2026 | ||
| Hateful meme classification | HarM (test) | 31 | Feb 26, 2026 | ||
| Image Classification | Describable Textures Dataset (DTD) (test) | 31 | Jul 8, 2026 | ||
| Domain Generalization | TerraInc (out-of-domain) | 31 | Feb 26, 2026 | ||
| Information Retrieval | Natural Questions (test) | 31 | Jun 12, 2026 | ||
| Classification | COCO | 31 | Apr 15, 2026 | ||
| Image Captioning | COCO | 31 | Feb 26, 2026 | ||
| Multimodal Sentiment Analysis | CMU-MOSEI | 31 | Jun 4, 2026 | ||
| Best Arm Identification | Unstructured instances K=40 | 31 | Feb 26, 2026 | ||
| Long-tailed Recognition | iNaturalist 2018 | 31 | May 12, 2026 | ||
| Offline Reinforcement Learning | D4RL HalfCheetah (Expert) | 31 | May 11, 2026 | ||
| Event TEMPREL extraction | MATRES | 31 | Mar 25, 2026 | ||
| Scene Classification | UCM 1.0 (train) | 31 | Feb 26, 2026 | ||
| Text-to-Image synthesis | MSCOCO | 31 | Feb 26, 2026 | ||
| OOD Detection | CIFAR-100 | 31 | Feb 26, 2026 | ||
| Targeted Adversarial Attack | ImageNet | 31 | Feb 26, 2026 | ||
| Task-incremental Learning | CIFAR100 (test) | 31 | Mar 10, 2026 | ||
| Long-term action anticipation | Ego4D v1 (test) | 31 | Feb 26, 2026 | ||
| Clustering | CIFAR100 | 31 | May 14, 2026 |