Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1331 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Stochastic Optimization Convergence | Theoretical Analysis | 23 | May 11, 2026 | ||
| Image Classification | ImageNet-R | 23 | Feb 26, 2026 | ||
| Image Classification | Stylized ImageNet (SIN) | 23 | Feb 26, 2026 | ||
| Image Classification | Carton | 23 | Feb 26, 2026 | ||
| Continuous Sign Language Recognition | CSL | 23 | Feb 26, 2026 | ||
| Scene Text Spotting | Total-Text | 23 | Feb 26, 2026 | ||
| End-to-end Text Spotting | Inverse-Text (test) | 23 | Feb 26, 2026 | ||
| Zero-shot Image Classification | ImageNet-R (test) | 23 | Feb 27, 2026 | ||
| Object Classification | SUN397 | 23 | Mar 4, 2026 | ||
| Image Classification | CIFAR-100 | 23 | Feb 26, 2026 | ||
| Audio-Visual Event Classification | VGGSound (test) | 23 | Apr 1, 2026 | ||
| Continuous Sign Language Recognition | CSL (test) | 23 | Feb 26, 2026 | ||
| Robust Classification | CivilComments | 23 | Feb 26, 2026 | ||
| Semantic Segmentation | SYNTHIA to Cityscapes 16 and 13 categories (val) | 23 | Feb 26, 2026 | ||
| Offline Model-based Optimization | D'Kitty Morphology Design-Bench | 23 | Mar 5, 2026 | ||
| Offline Model-based Optimization | Ant Morphology Design-Bench | 23 | Mar 5, 2026 | ||
| Capacitated Vehicle Routing Problem (CVRP) | CVRP n=200 Generalization 1K instances | 23 | Jun 30, 2026 | ||
| Offline Reinforcement Learning | D4RL Gym halfcheetah-random | 23 | May 12, 2026 | ||
| Deepfake Detection | FaceShifter (FSh) | 23 | May 15, 2026 | ||
| Environmental sound classification | Gunshot triangulation | 23 | Feb 26, 2026 | ||
| Aspect-level sentiment analysis | Rest15 | 23 | Feb 26, 2026 | ||
| Image Classification | ImageNet-LT | 23 | Feb 26, 2026 | ||
| Document Retrieval | NQ 100K | 23 | Feb 26, 2026 | ||
| Document Retrieval | NQ10K | 23 | Feb 26, 2026 | ||
| Image Classification | ImageNet 1k (val) | 23 | Feb 26, 2026 |