Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1752 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Open-Domain Question Answering | WebQuestions | 19 | Feb 26, 2026 | ||
| Face verification | CelebA-HQ | 19 | Feb 26, 2026 | ||
| Amodal Segmentation | D2SA | 19 | Feb 26, 2026 | ||
| Amodal Segmentation | COCOA cls | 19 | Feb 26, 2026 | ||
| Image Super-resolution | Set14 3x | 19 | Mar 13, 2026 | ||
| Image Super-resolution | Set5 3x | 19 | Mar 13, 2026 | ||
| General Visual Question Answering | MMBench-EN (test) | 19 | Feb 26, 2026 | ||
| Video Reasoning Segmentation | ReVOS (test) | 19 | Apr 14, 2026 | ||
| Pixel-level Anomaly Detection | MPDD | 19 | May 28, 2026 | ||
| Automatic Speech Recognition | LRS3 433-hour labeled (test) | 19 | Feb 26, 2026 | ||
| 3D Question Answering | NuscenesQA v1.0 (test) | 19 | Feb 26, 2026 | ||
| Video Grounding | E.T. Bench-Grounding (test) | 19 | Feb 26, 2026 | ||
| Image Editing | MagicBrush | 19 | May 20, 2026 | ||
| Vision-Language Evaluation | MMBench | 19 | Mar 11, 2026 | ||
| Human Pose Estimation | PoseTrack 2021 (test) | 19 | Mar 24, 2026 | ||
| Defect Localization | VisA | 19 | Apr 23, 2026 | ||
| Defect Classification | VisA | 19 | Feb 26, 2026 | ||
| Defect Classification | MVTec-AD | 19 | Feb 26, 2026 | ||
| Summarization | ACI-Bench | 19 | Feb 26, 2026 | ||
| Summarization | SAMSum | 19 | Feb 26, 2026 | ||
| Summarization | CNN | 19 | Feb 26, 2026 | ||
| Referring Image Segmentation | G-Ref u (val) | 19 | Feb 26, 2026 | ||
| Semantic Segmentation | ScanNet200 v1 (val) | 19 | Feb 27, 2026 | ||
| Facial Avatar Rendering | Multiview Video Face Capture Dataset (test) | 19 | Feb 26, 2026 | ||
| Oriented Object Detection | DroneVehicle (test) | 19 | Feb 26, 2026 |