Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1484 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Geolocation Inference Privacy Protection | DoxBench (test) | 21 | Feb 26, 2026 | ||
| Video Understanding | LongVideo | 21 | Feb 26, 2026 | ||
| Multimodal Understanding | Image Understanding Benchmarks MMB(EN), MMB(ZH), POPE, MMStar, MMMUVal, AI2D, MuirBench, BLINK, RealWorld | 21 | Feb 26, 2026 | ||
| Image Editing | ImgEdit (full) | 21 | Mar 5, 2026 | ||
| Classification | Describable Textures (DTD) | 21 | Jun 16, 2026 | ||
| Image Classification | Cifar10 | 21 | Feb 27, 2026 | ||
| Pan-sharpening | GaoFen2 | 21 | Mar 24, 2026 | ||
| Subject Re-identification | ChestXray-14 (test) | 21 | Feb 26, 2026 | ||
| 3D Reconstruction | Waymo | 21 | Jul 8, 2026 | ||
| Image Classification | Average across 10 datasets | 21 | Apr 3, 2026 | ||
| Deepfake Detection | Generalization Evaluation Suite | 21 | Feb 26, 2026 | ||
| Text-to-Image Generation | VISOR | 21 | Feb 26, 2026 | ||
| CT Reconstruction | LIDC 512 x 512 x 256 (test) | 21 | Feb 26, 2026 | ||
| CT Reconstruction | LIDC 256 x 256 x 256 (test) | 21 | Feb 26, 2026 | ||
| SPAD Estimation | Winter wheat (test) | 21 | Feb 26, 2026 | ||
| LAI Estimation | Winter wheat (test) | 21 | Feb 26, 2026 | ||
| Multimodal Understanding | Multimodal Evaluation Suite (GQA, MMBench, MMBench-CN, MME, POPE, SEED-Bench, TextVQA, VizWiz, OCRBench) | 21 | Feb 26, 2026 | ||
| Video Question Answering | VideoMME w/ sub | 21 | May 26, 2026 | ||
| Audio-Visual Segmentation | AVSBench AVS-Objects-MS3 | 21 | Feb 26, 2026 | ||
| Audio-Visual Segmentation | AVSBench AVS-Objects-S4 | 21 | Feb 26, 2026 | ||
| Camouflaged Object Detection | NC4K 1.0 | 21 | Feb 26, 2026 | ||
| Image Compression | DIV16K (Evaluation) | 21 | Feb 26, 2026 | ||
| AI-generated image detection | RealChain Chain Degradations | 21 | Apr 7, 2026 | ||
| Streaming Video Understanding | OVO-Bench 1.0 (test) | 21 | Apr 7, 2026 | ||
| Multidisciplinary Knowledge | MMMU | 21 | Feb 26, 2026 |