Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1014 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Fine-grained classification | EuroSAT base classes | 27 | Feb 27, 2026 | ||
| Fine-grained classification | DTD (base classes) | 27 | Feb 27, 2026 | ||
| Fine-grained classification | SUN397 (base classes) | 27 | Feb 27, 2026 | ||
| Fine-grained classification | FGVCAircraft (base classes) | 27 | Feb 27, 2026 | ||
| Fine-grained classification | Food101 (base classes) | 27 | Feb 27, 2026 | ||
| Fine-grained classification | OxfordPets (base classes) | 27 | Feb 27, 2026 | ||
| Fine-grained classification | Caltech101 (base classes) | 27 | Feb 27, 2026 | ||
| Graph Edit Distance Approximation | PTC MR | 27 | Feb 26, 2026 | ||
| Graph Edit Distance Approximation | MUTAG | 27 | Feb 26, 2026 | ||
| Medical Image Classification | Retinopathy (test) | 27 | Feb 26, 2026 | ||
| Medical Image Classification | DermaTri (test) | 27 | Feb 26, 2026 | ||
| Medical Image Classification | Melanoma (test) | 27 | Feb 26, 2026 | ||
| Medical Image Classification | Glaucoma (test) | 27 | Feb 26, 2026 | ||
| Medical Image Classification | Edema (test) | 27 | Feb 26, 2026 | ||
| Mobile GUI Agent Decision Making | AndroidWorld | 27 | May 12, 2026 | ||
| Retrieval | QAMPARI N=1000 (test) | 27 | Feb 26, 2026 | ||
| Instruction Following | AlpacaFarm | 27 | Apr 6, 2026 | ||
| Offline Reinforcement Learning | D4RL Antmaze | 27 | May 27, 2026 | ||
| Semantic Segmentation | Trans10K v2 | 27 | Feb 26, 2026 | ||
| 3D Object Detection | KITTI (test) | 27 | Feb 26, 2026 | ||
| DR estimation | Simulation configuration (ii) imbalanced scenario 2 (heterogeneous) | 27 | Feb 26, 2026 | ||
| DR estimation | Simulation configuration (ii) imbalanced scenario 1 (homogeneous) | 27 | Feb 26, 2026 | ||
| 3D Object Detection | nuScenes Rainy (val) | 27 | Jun 19, 2026 | ||
| Text Rendering | LongText-Bench Chinese | 27 | May 29, 2026 | ||
| Classification | Adult | 27 | May 20, 2026 |