Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2539 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Multimodal Evaluation | SEED Image | 15 | Feb 26, 2026 | ||
| Semantic Segmentation | MosMed | 15 | Feb 26, 2026 | ||
| Semantic Segmentation | AutoPET | 15 | Feb 26, 2026 | ||
| Object Hallucination Evaluation | HallB (Hallucination-Bench) | 15 | Feb 26, 2026 | ||
| Point Cloud Reconstruction | DTU 1 (test) | 15 | Feb 26, 2026 | ||
| SLAM | TUM RGB-D (fr3-office) | 15 | Feb 26, 2026 | ||
| Novel View Synthesis | Simulated dataset | 15 | Feb 26, 2026 | ||
| Depth Estimation | Captured Lidar Scenes hardware prototype (depth evaluation) | 15 | Feb 26, 2026 | ||
| Novel View Synthesis | Captured Lidar Scenes novel views hardware prototype | 15 | Feb 26, 2026 | ||
| Depth Estimation | Simulated scenes | 15 | Feb 26, 2026 | ||
| Semantic Sketch Segmentation | FS-COCO (test) | 15 | Jun 11, 2026 | ||
| Object Detection | MS COCO 2014 (test) | 15 | Feb 26, 2026 | ||
| 3D Human Reconstruction (Normals Back) | Monocular 3D Human Reconstruction (test) | 15 | Feb 26, 2026 | ||
| 3D Human Reconstruction (Normals Front) | Monocular 3D Human Reconstruction (test) | 15 | Feb 26, 2026 | ||
| 3D Human Reconstruction | Monocular 3D Human Reconstruction (test) | 15 | Feb 26, 2026 | ||
| Gait Recognition | CASIA-B Bag Carrying (#1-2) | 15 | Feb 26, 2026 | ||
| Image Classification | ImageNet 1k (val) | 15 | Feb 26, 2026 | ||
| Object Classification | ImageNet (test) | 15 | Feb 26, 2026 | ||
| Long-tailed Recognition | ImageNet-LT (test) | 15 | Feb 26, 2026 | ||
| Person Identification | ACC-MM1-Activities (same-activity) | 15 | Feb 26, 2026 | ||
| Person Identification | Charades-AB (same-activity) | 15 | Feb 26, 2026 | ||
| Person Identification | PKU MMD-AB View+ (same-activity) | 15 | Feb 26, 2026 | ||
| Person Identification | NTU RGB-AB View+ (same-activity) | 15 | Feb 26, 2026 | ||
| Iterative Vision-and-Language Navigation | IR2R-CE (val seen) | 15 | Feb 26, 2026 | ||
| Image Classification | EMNIST Letters (test) | 15 | Mar 24, 2026 |