Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1244 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Forecasting | PEMS-04 | 24 | Feb 26, 2026 | ||
| Forecasting | PEMS-BAY | 24 | Feb 26, 2026 | ||
| Image Classification | STL-10 | 24 | Feb 26, 2026 | ||
| Multimodal Code Generation | UniSVG-ISVGEN | 24 | Jul 1, 2026 | ||
| Camera movement understanding | CameraBench 10K-sample VQA subset 1.0 (test) | 24 | Feb 26, 2026 | ||
| AI-Generated Image Detection | GenImage 1.0 (test) | 24 | Feb 26, 2026 | ||
| Image Classification | ImageNet-S | 24 | Mar 4, 2026 | ||
| Video Reasoning | LVBench | 24 | Feb 26, 2026 | ||
| Video Reasoning | LongVideoBench | 24 | Jun 11, 2026 | ||
| Visual Metaphor Transfer | Curated Visual Metaphor Dataset (test) | 24 | Feb 26, 2026 | ||
| AIGI Detection | RRDataset | 24 | Apr 7, 2026 | ||
| 3D LiDAR Scene Completion | Apollo (sequence 00) | 24 | Feb 26, 2026 | ||
| Image Generation | MS-COCO 10k (test) | 24 | Mar 4, 2026 | ||
| Alignment Quality Assessment | AIGCIQA2023 (test) | 24 | Feb 26, 2026 | ||
| Video Object Segmentation | ReVOS (Overall) | 24 | Apr 27, 2026 | ||
| Image Generation | ImageNet 2009 (val) | 24 | Feb 26, 2026 | ||
| Action Recognition | UCF101 PR (test) | 24 | Feb 26, 2026 | ||
| Hallucination Mitigation | CHAIR | 24 | Feb 26, 2026 | ||
| Human Preference Evaluation | HPS v2.1 | 24 | Mar 4, 2026 | ||
| Polyp Segmentation | PolypGen | 24 | May 19, 2026 | ||
| Egocentric Spatial Reasoning | 3DSRBench Egocentric (test) | 24 | Feb 26, 2026 | ||
| Fine-grained visual understanding | HR-Bench 4K | 24 | Feb 26, 2026 | ||
| 3D Object Detection | nuScenes-C (val) | 24 | Mar 9, 2026 | ||
| SLAM | ROTIO | 24 | Feb 26, 2026 | ||
| Low-Light Video Enhancement | DID | 24 | Jun 11, 2026 |