Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2101 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Continual Learning | PMNIST (test) | 17 | Feb 26, 2026 | ||
| Robust Verification | MNIST (test) | 17 | Feb 26, 2026 | ||
| Natural Language Inference | SciTail (dev) | 17 | Feb 26, 2026 | ||
| Classification | Google commands | 17 | May 25, 2026 | ||
| Retrosynthesis prediction | USPTO-MIT | 17 | Feb 26, 2026 | ||
| Graph Anomaly Detection | Amazon (1%) | 17 | Jun 16, 2026 | ||
| Molecular Docking | PDBBind (unseen receptors) | 17 | Feb 26, 2026 | ||
| DFT energy prediction | AgAu | 17 | Feb 26, 2026 | ||
| DFT energy prediction | KIM Si | 17 | Feb 26, 2026 | ||
| Shear moduli prediction | Materials Project (test) | 17 | Feb 26, 2026 | ||
| Graph Retrieval | MR (test) | 17 | Feb 26, 2026 | ||
| Graph Retrieval | MM (test) | 17 | Feb 26, 2026 | ||
| Graph Retrieval | FR (test) | 17 | Feb 26, 2026 | ||
| Audio Classification | VC1 | 17 | Feb 26, 2026 | ||
| Target Sound Extraction | FSDKaggle 2018 (test) | 17 | Feb 26, 2026 | ||
| Target Sound Extraction | MUSIC21 (test) | 17 | Feb 26, 2026 | ||
| Vision-Language Evaluation | CV-Bench | 17 | Feb 26, 2026 | ||
| 3D Object Detection | Waymo Open single-frame (val) | 17 | Feb 26, 2026 | ||
| Hand Gesture Recognition | NVGesture 2016 (test) | 17 | Feb 26, 2026 | ||
| Co-speech gesture generation | BEAT-2 (1 Speaker) | 17 | Feb 26, 2026 | ||
| REC | ColonINST (unseen) | 17 | Feb 26, 2026 | ||
| REC | ColonINST (seen) | 17 | Feb 26, 2026 | ||
| REG | ColonINST (unseen) | 17 | Feb 26, 2026 | ||
| REG | ColonINST (seen) | 17 | Feb 26, 2026 | ||
| CLS | ColonINST (unseen) | 17 | Feb 26, 2026 |