Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 712 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Temporal Action Localization | THUMOS14 v1.0 (50%-50%) | 34 | May 22, 2026 | ||
| Pansharpening | GaoFen-2 (GF2) full-resolution original (test) | 34 | Jun 17, 2026 | ||
| Trajectory Prediction | Stanford Drone Dataset (SDD) | 34 | Mar 27, 2026 | ||
| Image Deraining | 100 (test) | 34 | Jun 23, 2026 | ||
| Video Reconstruction | Bunny | 34 | Feb 26, 2026 | ||
| Video-Text Retrieval | MSR-VTT | 34 | Jun 9, 2026 | ||
| Text-to-Image Generation | MS-COCO 5K 2017 (val) | 34 | Feb 26, 2026 | ||
| LLM Judge Agreement | MT-bench First Turn | 34 | Feb 26, 2026 | ||
| Image Denoising | BSD68 σ = 50 | 34 | Jun 18, 2026 | ||
| Image Denoising | BSD68 σ = 15 | 34 | Jun 18, 2026 | ||
| Transductive future link prediction | SocialEvol. | 34 | Jul 7, 2026 | ||
| Transductive future link prediction | UCI | 34 | Jul 7, 2026 | ||
| Transductive future link prediction | MOOC | 34 | Jul 7, 2026 | ||
| Transductive future link prediction | Wikipedia | 34 | Jul 7, 2026 | ||
| Semantic Segmentation | Pascal VOC VOC-20 (test) | 34 | Feb 26, 2026 | ||
| Natural Language Understanding | ARC-c | 34 | May 12, 2026 | ||
| Exemplar-Free Class-Incremental Learning | ImageNet Subset | 34 | Jun 26, 2026 | ||
| LiDAR Semantic Segmentation | ScribbleKITTI (train) | 34 | Feb 26, 2026 | ||
| Action Recognition | UAV-Human | 34 | Mar 9, 2026 | ||
| Object Detection | M³FD (test) | 34 | Feb 26, 2026 | ||
| Multi-objective Knapsack Problem | Bi-KP n=200 | 34 | May 25, 2026 | ||
| Multi-objective Knapsack Problem | Bi-KP n=100 | 34 | May 25, 2026 | ||
| Multi-objective Knapsack Problem | Bi-KP n=50 | 34 | May 25, 2026 | ||
| Text-to-Image Generation | MS-COCO 5k samples Stable Diffusion v1.5 (test) | 34 | Feb 26, 2026 | ||
| Disentanglement | Shapes3D | 34 | Jul 7, 2026 |