Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1048 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Camouflaged Object Detection | CHAMELEON (76) | 26 | May 26, 2026 | ||
| 3D Medical Image Segmentation | LA 16 labeled / 64 unlabeled | 26 | May 26, 2026 | ||
| Image Demorphing | StyleGAN | 26 | May 26, 2026 | ||
| Image Demorphing | Wmorph | 26 | May 26, 2026 | ||
| Image Demorphing | MorDiff | 26 | May 26, 2026 | ||
| Image Demorphing | FMorph | 26 | May 26, 2026 | ||
| Image Demorphing | OpenCV | 26 | May 26, 2026 | ||
| Image Demorphing | AMSL | 26 | May 26, 2026 | ||
| Image Classification | ImageNet-1K 16 (train) | 26 | May 26, 2026 | ||
| Classification | Higgs | 26 | May 26, 2026 | ||
| Classification | QoE | 26 | May 26, 2026 | ||
| Regression | RSS | 26 | May 26, 2026 | ||
| Regression | VoD | 26 | May 26, 2026 | ||
| Regression | KVS | 26 | May 26, 2026 | ||
| General Reasoning and Coding | Mean GSM8K, HumanEval, MBPP | 26 | May 26, 2026 | ||
| Code Generation | HumanEval | 26 | May 26, 2026 | ||
| Mathematical Reasoning | GSM8K | 26 | May 26, 2026 | ||
| Homogeneous Node Classification | Arxiv | 26 | May 26, 2026 | ||
| Homogeneous Node Classification | Cora | 26 | May 26, 2026 | ||
| Planning | Blocksworld | 26 | Jul 7, 2026 | ||
| Fact Generation (Arbitrary Masking) | WikiPeople | 26 | May 26, 2026 | ||
| Fact Generation (Targeted) | WikiPeople | 26 | May 26, 2026 | ||
| Fact Generation (Scratch) | WikiPeople | 26 | May 26, 2026 | ||
| Fine-grained Perception | HRBench 4K | 26 | May 28, 2026 | ||
| High-Resolution Image Perception | HR-Bench 8K | 26 | May 25, 2026 |