Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 807 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Medical Image Segmentation | ISLES T0 (test) | 31 | Apr 2, 2026 | ||
| Point-level recovery | KITTI-J | 31 | Apr 2, 2026 | ||
| Point-level recovery | nuScenes-J | 31 | Apr 2, 2026 | ||
| Web-based Agent Interaction | WebShop (val) | 31 | Apr 14, 2026 | ||
| Crack Segmentation | Crack500 | 31 | Jun 23, 2026 | ||
| Backdoor Attack in Dataset Condensation | STL10 | 31 | Apr 1, 2026 | ||
| Camera Understanding | MegaDepth | 31 | May 15, 2026 | ||
| Image Classification | Scene | 31 | Mar 31, 2026 | ||
| Audio Question-Answering | MMSU | 31 | Jun 9, 2026 | ||
| Common Sense Reasoning and Question Answering | Reasoning Benchmarks Zero-shot (PIQA, ARC, HellaSwag, WinoGrande) | 31 | Mar 27, 2026 | ||
| OOD Detection | ImageNet-1k (ID) vs Sun (OOD) 1.0 (test) | 31 | Mar 27, 2026 | ||
| Financial Tool-Use | FinToolBench | 31 | Mar 26, 2026 | ||
| Frame-level Deepfake Detection | Celeb-DF v2 | 31 | Apr 21, 2026 | ||
| Sudoku solving | Sudoku-Extreme (test) | 31 | May 21, 2026 | ||
| Image Reconstruction | ImageNet-1k 256x256 | 31 | Jun 1, 2026 | ||
| Relation Extraction | Zero-Shot RE WikiData (test) | 31 | Apr 15, 2026 | ||
| Human Preference Alignment | PKU-SafeRLHF | 31 | Mar 23, 2026 | ||
| Web Navigation | WebArena Lite | 31 | Jun 12, 2026 | ||
| Interactive decision making | Virtualhome | 31 | Jun 11, 2026 | ||
| Elevation reconstruction | IARPA 3D Mapping Challenge | 31 | May 14, 2026 | ||
| Elevation reconstruction | DFC 2019 | 31 | May 14, 2026 | ||
| Image Classification | SUN397 | 31 | Apr 1, 2026 | ||
| Object Detection | LEVIR-Ship (test) | 31 | Mar 20, 2026 | ||
| Change Detection | OSCD (test) | 31 | Mar 20, 2026 | ||
| Verilog Code Generation | RTLLM v1.1 | 31 | Apr 13, 2026 |