Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1242 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| 4× Super-Resolution | DIV2K (test) | 24 | Jun 29, 2026 | ||
| Light field data compression | Knights light field data | 24 | Feb 26, 2026 | ||
| Light field data compression | Bunny light field data | 24 | Feb 26, 2026 | ||
| Multimodal Perception and Reasoning | FCMBench 1.0 (test) | 24 | Feb 26, 2026 | ||
| Image Classification | Average | 24 | May 15, 2026 | ||
| VQA Hallucination Detection | POPE Average of Random, Popular, and Adversarial 2023 | 24 | Feb 26, 2026 | ||
| Few-shot 3D Point Cloud Semantic Segmentation | ScanNet v2 | 24 | Feb 26, 2026 | ||
| 3D point cloud semantic segmentation | ScanNet Mean Fold official | 24 | Feb 26, 2026 | ||
| Audio-Driven Facial Animation | RAVDESS 42 (test) | 24 | Feb 26, 2026 | ||
| Image Segmentation | LVIS LQ-1 (test) | 24 | Apr 27, 2026 | ||
| Image Segmentation | LVIS LQ-2 (test) | 24 | Apr 27, 2026 | ||
| Image Segmentation | LVIS LQ-3 (test) | 24 | Apr 27, 2026 | ||
| Image Segmentation | ThinObject-5K LQ-1 (test) | 24 | Apr 27, 2026 | ||
| Image Segmentation | ThinObject-5K LQ-2 (test) | 24 | Apr 27, 2026 | ||
| Image Segmentation | ThinObject-5K LQ-3 (test) | 24 | Apr 27, 2026 | ||
| Video Super-Resolution | SDE out | 24 | Feb 26, 2026 | ||
| Video Super-Resolution | SDE-in | 24 | Feb 26, 2026 | ||
| Video Super-Resolution | SDSD out | 24 | Feb 26, 2026 | ||
| Video Super-Resolution | SDSD-in | 24 | Feb 26, 2026 | ||
| Adversarial Video Purification | HMDB-51 | 24 | Feb 26, 2026 | ||
| Adversarial Video Purification | UCF-101 | 24 | Feb 26, 2026 | ||
| Adversarial Video Purification | HMDB-51 (test) | 24 | Feb 26, 2026 | ||
| Adversarial Video Purification | UCF-101 (test) | 24 | Feb 26, 2026 | ||
| Face Forgery Detection | S2CFP (test) | 24 | Feb 26, 2026 | ||
| Physical Reasoning | PhyX | 24 | May 15, 2026 |