Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1423 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Adversarial Attack | ImageNet | 21 | Jul 9, 2026 | ||
| Video Enhancement | JCT-VC | 21 | Jul 9, 2026 | ||
| Image Classification | ImageNet-100 70% Compression (test) | 21 | Jul 9, 2026 | ||
| Distance-level row-wise correlation | Swiss roll Non-uniform sampling (Beta(1, 4)) analytic geodesic ground truth | 21 | Jul 8, 2026 | ||
| Distance-level row-wise correlation | Swiss roll Uniform sampling analytic geodesic ground truth | 21 | Jul 8, 2026 | ||
| Text-to-Image Generation | VSA | 21 | Jul 8, 2026 | ||
| Text-to-Image Generation | RAB | 21 | Jul 8, 2026 | ||
| Text-to-Image Generation | MMA | 21 | Jul 8, 2026 | ||
| Text-to-Image Generation | I2P | 21 | Jul 8, 2026 | ||
| Polyp Segmentation | Five Standard Polyp Datasets (FSPD) | 21 | Jul 8, 2026 | ||
| Evidence-Based Fact-Checking | AMBIFC | 21 | Jul 7, 2026 | ||
| Patient Discharge Disposition Prediction | PDDP | 21 | Jul 7, 2026 | ||
| Hallucination Evaluation | Style-CHAIR | 21 | Jul 7, 2026 | ||
| Image-Text Retrieval | DocVQA | 21 | Jul 7, 2026 | ||
| Image-Text Retrieval | ImageCoDe | 21 | Jul 7, 2026 | ||
| Image-Text Retrieval | MSCOCO | 21 | Jul 7, 2026 | ||
| Image-Text Retrieval | Flickr30K | 21 | Jul 7, 2026 | ||
| Multimodal Continual Learning | MRCL 1.0 (test) | 21 | Jul 7, 2026 | ||
| Open-ended Generative VQA | IRIS-120K Generative Overall | 21 | Jul 7, 2026 | ||
| Open-ended Generative VQA | IRIS-120K Scene-VQA | 21 | Jul 7, 2026 | ||
| Open-ended Generative VQA | IRIS-120K Tree-VQA | 21 | Jul 7, 2026 | ||
| Visual Question Answering | IRIS 120K (Multi split) | 21 | Jul 7, 2026 | ||
| Visual Question Answering | IRIS-120K (Single split) | 21 | Jul 7, 2026 | ||
| Visual Question Answering | IRIS-120K (Judge) | 21 | Jul 7, 2026 | ||
| Syndrome Differentiation | TCM-SD | 21 | Jul 7, 2026 |