Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1100 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Open-vocabulary semantic segmentation | Pascal Context 59 (P59) | 25 | Jun 16, 2026 | ||
| Surface-completion | BTC (test) | 25 | Jun 16, 2026 | ||
| Authenticity score prediction | AIGCIQA 2023 | 25 | Jun 16, 2026 | ||
| Multimodal Classification | Kinetics-Sounds | 25 | Jun 16, 2026 | ||
| Perception and Cognition Evaluation | MME | 25 | Jun 16, 2026 | ||
| Visual Question Answering | GQA | 25 | Jun 16, 2026 | ||
| Object Detection | PSP Plane | 25 | Jun 16, 2026 | ||
| Object Detection | PSP.Ship (test) | 25 | Jun 16, 2026 | ||
| Underwater Image Enhancement | Underwater Image Enhancement Efficiency Benchmark | 25 | Jun 16, 2026 | ||
| Exploit Generation | RCE vulnerabilities input level 5 | 25 | Jun 16, 2026 | ||
| Semantic Segmentation | COCO-Stuff 9 (val) | 25 | Jun 15, 2026 | ||
| Semantic Segmentation | SUN-RGBD 70 (test) | 25 | Jun 15, 2026 | ||
| Semantic Segmentation | NYU v2 68 (test) | 25 | Jun 15, 2026 | ||
| Multi-step prediction | Quad-Link | 25 | Jun 15, 2026 | ||
| 1D Function Approximation | 1D approximation benchmark (test) | 25 | Jun 12, 2026 | ||
| 1D Function Approximation | 1D approximation benchmark (train) | 25 | Jun 12, 2026 | ||
| Adversarial Motion Generation | HDM05 | 25 | Jun 12, 2026 | ||
| Adversarial Attack | 100STYLE (test) | 25 | Jun 12, 2026 | ||
| Lifelong Unlearning | MLUBench Task A | 25 | Jun 12, 2026 | ||
| Diameter estimation | Metal dataset washers (test) | 25 | Jun 12, 2026 | ||
| High-level planning | VLABench vlm_evaluation 1.0 (test) | 25 | Jun 11, 2026 | ||
| Video Spatial Understanding | VSI-Bench 500 QA 1.0 | 25 | Jun 11, 2026 | ||
| GUI grounding | ScreenSpot Pro | 25 | Jun 11, 2026 | ||
| Image Denoising | Baboon | 25 | Jun 11, 2026 | ||
| Image Denoising | Hill image | 25 | Jun 11, 2026 |