Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2074 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Pose estimation | NuScenes | 17 | Mar 16, 2026 | ||
| Medical Image Classification | BreaKHis downsampling eighth x8↓ | 17 | Feb 26, 2026 | ||
| Medical Image Classification | BreaKHis downsampling quarter (x4↓) | 17 | Feb 26, 2026 | ||
| Medical Image Classification | BreaKHis downsampling half (x2↓) | 17 | Feb 26, 2026 | ||
| Medical Image Classification | BreaKHis high-resolution | 17 | Feb 26, 2026 | ||
| CT Denoising | CT (test) | 17 | Feb 26, 2026 | ||
| MRI Super-Resolution | MRI (test) | 17 | Feb 26, 2026 | ||
| Image Classification | BAR (test) | 17 | Feb 26, 2026 | ||
| Relative Pose Estimation | MegaDepth 1500 outdoor pairs (test) | 17 | Feb 26, 2026 | ||
| Relative Pose Estimation | MegaDepth 1500 pairs (test) | 17 | Feb 26, 2026 | ||
| Theory of Mind reasoning | MMToM-QA Text-only | 17 | May 12, 2026 | ||
| Question Answering | COTEMPQA 1.0 (test) | 17 | Feb 27, 2026 | ||
| Image Captioning Evaluation | COMPOSITE (COM) (test) | 17 | Feb 26, 2026 | ||
| Reward Modeling | Reward Bench Prior Sets | 17 | Feb 26, 2026 | ||
| 3D Human Pose Reconstruction | AMASS (Setting S2) | 17 | Jun 23, 2026 | ||
| Multimodal Entity Linking | WikiMEL (test) | 17 | Feb 26, 2026 | ||
| Scholarly Title Generation | LaMP-5 1.0 (test) | 17 | Mar 4, 2026 | ||
| Text Classification | EDOS (test) | 17 | Feb 26, 2026 | ||
| Diabetic Retinopathy Classification | Messidor (test) | 17 | Mar 20, 2026 | ||
| Object Detection | BBBC006 | 17 | May 25, 2026 | ||
| Code Completion | RepoBench-P | 17 | May 25, 2026 | ||
| Capacitated Vehicle Routing Problem | CVRP n=100 (train) | 17 | Jun 11, 2026 | ||
| Vision-language tracking | WebUOT-1M | 17 | Feb 26, 2026 | ||
| Deraining | real (test) | 17 | Feb 26, 2026 | ||
| Deblurring | RealBlur-J | 17 | Feb 26, 2026 |