Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2523 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Concept Erasure | Van-Gogh artistic style 1.4 (test) | 15 | Feb 26, 2026 | ||
| Regression | Cali-Housing | 15 | Feb 27, 2026 | ||
| Regression | Population | 15 | Feb 27, 2026 | ||
| Regression | Temperature | 15 | Feb 27, 2026 | ||
| Classification | EcoRegions | 15 | Feb 27, 2026 | ||
| Text-to-Image Generation | MS-COCO 10K (val) | 15 | Feb 26, 2026 | ||
| Image Reconstruction | DIV2K (test) | 15 | Jul 3, 2026 | ||
| Universal Adversarial Attack | ImageNet | 15 | Feb 26, 2026 | ||
| Universal Adversarial Attack | ImageNet (val) | 15 | Feb 26, 2026 | ||
| Knowledge modification | WikiData counterfact | 15 | Feb 26, 2026 | ||
| Knowledge modification | WikiBio | 15 | Feb 26, 2026 | ||
| Semantic Segmentation | ADE20K 100-10 (6) | 15 | Feb 26, 2026 | ||
| Novel View Synthesis | 360Roam (test) | 15 | Jun 30, 2026 | ||
| Sign Language Recognition | LSA 64 (test) | 15 | Jun 4, 2026 | ||
| Deepfake Detection | FF++ Intra-dataset (c40) | 15 | Feb 26, 2026 | ||
| Few-shot Image Classification | Flowers102 (test) | 15 | Feb 26, 2026 | ||
| Few-shot Image Classification | OxfordPets (test) | 15 | Feb 26, 2026 | ||
| Few-shot Image Classification | Caltech101 (test) | 15 | Feb 26, 2026 | ||
| Few-shot Image Classification | ImageNet (test) | 15 | Feb 26, 2026 | ||
| Semantic Segmentation | ADE20K 70 (val) | 15 | Jul 2, 2026 | ||
| Composed Image Retrieval | CIRR 1.0 (val) | 15 | Feb 26, 2026 | ||
| Novel View Synthesis | DTU 15 (test) | 15 | Feb 26, 2026 | ||
| MLLM Jailbreaking | MM-SafetyBench Physical Harm scenario | 15 | Feb 26, 2026 | ||
| Image Super-Resolution | ImageNet (val) | 15 | May 27, 2026 | ||
| Camera pose estimation | Replica | 15 | Apr 6, 2026 |