Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1056 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Dynamic Texture Recognition | UCLA Dataset | 26 | Apr 20, 2026 | ||
| Multi-task (Building, Road, Flood) | Average | 26 | Apr 20, 2026 | ||
| Road Extraction | DeepGlobe | 26 | Apr 20, 2026 | ||
| Building Extraction | WHU Sat. II | 26 | Apr 20, 2026 | ||
| Mathematical Reasoning | Average AIME24, AIME25, AMC23, MATH500 | 26 | Jun 30, 2026 | ||
| 6-DoF Pose Estimation | BOP LM-O, TUD-L, IC-BIN, HB, YCB-V | 26 | May 11, 2026 | ||
| UI Element Grounding | ScreenSpot Overall v2 | 26 | Apr 16, 2026 | ||
| Hand gesture classification | Ninapro DB4 | 26 | Apr 16, 2026 | ||
| Gesture Recognition | Ninapro DB7 | 26 | Apr 16, 2026 | ||
| Gesture Recognition | Ninapro DB2 | 26 | Apr 16, 2026 | ||
| Visual Emotion Recognition | 26 | Apr 15, 2026 | |||
| Visual Emotion Recognition | Flickr | 26 | Apr 15, 2026 | ||
| Visual Understanding | ScienceQA, TextVQA, and GQA | 26 | Apr 15, 2026 | ||
| Visual Reasoning | LogicVista | 26 | Apr 28, 2026 | ||
| Visual Reasoning | DynaMath | 26 | Apr 15, 2026 | ||
| Simple Question Answering | PopQA | 26 | Jun 30, 2026 | ||
| Text-to-Satellite Image Retrieval | CVG-Text Brisbane | 26 | Jun 23, 2026 | ||
| Question Answering | WebQ-QA Out-of-Domain (test) | 26 | Apr 14, 2026 | ||
| Question Answering | NQ-Open In-Domain (test) | 26 | Apr 14, 2026 | ||
| Question Answering | TVQA In-Domain (test) | 26 | Apr 14, 2026 | ||
| Trajectory Prediction | NGSIM | 26 | May 25, 2026 | ||
| Head Pose Estimation | BIWI cross-domain | 26 | Apr 14, 2026 | ||
| Mammography Classification | CSAW | 26 | Apr 14, 2026 | ||
| Mammography Classification | HCTP | 26 | Apr 14, 2026 | ||
| Knowledge corruption traceback | MS-MARCO | 26 | Apr 14, 2026 |