Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1691 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Embodied physical environment decision-making | ALFWorld | 19 | Jun 23, 2026 | ||
| Multilingual text query safety | PolyGuardPrompts | 19 | Jul 3, 2026 | ||
| Reaction Classification | Enzyme Reaction | 19 | Jun 23, 2026 | ||
| Action Classification | Penn Action | 19 | Jun 23, 2026 | ||
| Reinforcement Learning | Autonomous Driving Dataset | 19 | Jun 23, 2026 | ||
| Medical Image Segmentation | DIANE N=18 (train) | 19 | Jun 23, 2026 | ||
| Medical Image Segmentation | Spleen (N=34) (train) | 19 | Jun 23, 2026 | ||
| Medical Image Segmentation | FeTA (N=39) (train) | 19 | Jun 23, 2026 | ||
| Medical Image Segmentation | BraTS (N=387) (train) | 19 | Jun 23, 2026 | ||
| Visual Question Answering | NetQ | 19 | Jun 23, 2026 | ||
| Underexposure Correction | UndExp-Web | 19 | Jun 23, 2026 | ||
| Underexposure Correction | VE-LOL-L-Cap | 19 | Jun 23, 2026 | ||
| Overexposure Correction | Flickr OverExp | 19 | Jun 23, 2026 | ||
| Overexposure Correction | OverExp-Pair | 19 | Jun 23, 2026 | ||
| Link Prediction | DY | 19 | Jul 1, 2026 | ||
| Node Classification | WikiCS | 19 | Jun 19, 2026 | ||
| GUI Agent Task | MemGUI-Bench (Overall) | 19 | Jun 19, 2026 | ||
| GUI Agent Task | MemGUI-Bench Hard | 19 | Jun 19, 2026 | ||
| GUI Agent Task | MemGUI-Bench Medium | 19 | Jun 19, 2026 | ||
| GUI Agent Task | MemGUI-Bench Easy | 19 | Jun 19, 2026 | ||
| E-commerce shopping agent | ShoppingBench | 19 | Jun 19, 2026 | ||
| Robot Manipulation | LIBERO | 19 | Jun 19, 2026 | ||
| Socio-economic ranking comparison | G20 countries 2021 | 19 | Jun 19, 2026 | ||
| Visual SLAM | UWE dataset | 19 | Jun 18, 2026 | ||
| Linear Regression | wine (val) | 19 | Jun 18, 2026 |