Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1401 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Question Answering | OpenBookQA (dev) | 22 | Feb 26, 2026 | ||
| Semantic Textual Similarity | CDSC-R (test) | 22 | Feb 26, 2026 | ||
| Semantic Textual Similarity | CDSC-R (val) | 22 | Feb 26, 2026 | ||
| OOD Detection | ImageNet-1K Dfar | 22 | Feb 26, 2026 | ||
| Natural Language Understanding | GLUE RoBERTa LARGE (test dev) | 22 | Feb 26, 2026 | ||
| Natural Language Understanding | Ag_news, Subj, MR, Boolq, RTE (test) | 22 | Feb 26, 2026 | ||
| Sepsis Prediction | Sepsis (test) | 22 | Jun 9, 2026 | ||
| Image-to-Text Retrieval | Flickr8k | 22 | Feb 26, 2026 | ||
| Marine Animal Segmentation | RUWI | 22 | Feb 26, 2026 | ||
| Marine Animal Segmentation | UFO120 | 22 | Feb 26, 2026 | ||
| Multi-Classification | LIAR Closed | 22 | Feb 26, 2026 | ||
| Binary Classification | LIAR Open | 22 | Feb 26, 2026 | ||
| Code Generation | CodeContest | 22 | Apr 28, 2026 | ||
| Analogy Generation | UNIT 4 | 22 | Feb 26, 2026 | ||
| Unsupervised open-vocabulary semantic segmentation | Pascal Context (val) | 22 | Feb 26, 2026 | ||
| Image Classification | CIFAR-100 long-tailed (rho=100) (test) | 22 | Feb 26, 2026 | ||
| Open Ended Question Answering | MSVD | 22 | Feb 26, 2026 | ||
| Out-of-Distribution Detection | SVHN → CIFAR-100 (test) | 22 | Feb 26, 2026 | ||
| Classification | 12 Remote Sensing Datasets Average various (test) | 22 | Feb 26, 2026 | ||
| Classification | RSI-CB 128x128 (test) | 22 | Feb 26, 2026 | ||
| Object-Centric Learning | MOVi-E | 22 | Mar 13, 2026 | ||
| Corrupted Image Classification and OOD Detection | ImageNet-C 1.0 (test) | 22 | Feb 26, 2026 | ||
| Multi-label chest disease diagnosis | Chest X-ray | 22 | Feb 26, 2026 | ||
| DR grading | EyeQ | 22 | Feb 26, 2026 | ||
| Zero-shot Evaluation | OpenCLIP 38 datasets | 22 | Feb 26, 2026 |