Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2529 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Online Continual Learning | MNIST (5/2) | 15 | Feb 27, 2026 | ||
| Meta-continual learning | CIFAR10 (5/2) | 15 | Feb 27, 2026 | ||
| Image Classification | ImageNet-1K 1.0 (val) | 15 | Feb 26, 2026 | ||
| Multimodal Understanding | OpenCompass | 15 | May 1, 2026 | ||
| Diagram-to-Code | DiagramGen (test) | 15 | Feb 26, 2026 | ||
| Novel View Synthesis | DyCheck (test) | 15 | Feb 26, 2026 | ||
| SLAM Tracking | ReplicaMultiagent | 15 | Feb 26, 2026 | ||
| Human Image Animation | TikTok (test) | 15 | May 19, 2026 | ||
| Open-Vocabulary Semantic Segmentation | ADE-150 | 15 | Apr 15, 2026 | ||
| Box Inpainting | ImageNet 256 x 256 (val) | 15 | May 28, 2026 | ||
| Node Anomaly Detection | Yelp | 15 | Jun 9, 2026 | ||
| Jailbreak Attack | JailbreakBench PAIR | 15 | Apr 14, 2026 | ||
| LLM Alignment | SHP | 15 | Feb 26, 2026 | ||
| Motion In-between | Motion-X | 15 | Feb 27, 2026 | ||
| Motion Prediction | Motion-X | 15 | Feb 27, 2026 | ||
| Quantization | LLAMA v1 (train) | 15 | Feb 26, 2026 | ||
| Visual Speech Recognition | WildVSR | 15 | Feb 26, 2026 | ||
| Automatic Speech Recognition | LRS3 Low-Resource 30h labelled v1 (test) | 15 | Feb 26, 2026 | ||
| Novel View Synthesis | NeRF On-the-go | 15 | Jun 30, 2026 | ||
| Language Modeling | Specialized dataset Pile | 15 | Feb 26, 2026 | ||
| Language Modeling | Generic dataset | 15 | Feb 26, 2026 | ||
| Tabular Data Synthesis | collins | 15 | Feb 26, 2026 | ||
| Tabular Data Synthesis | collins | 15 | Feb 26, 2026 | ||
| Multiple-Choice Video QA | VideoMME | 15 | Feb 26, 2026 | ||
| Visual Question Answering | OVEN Query 1.0 (test) | 15 | Feb 26, 2026 |