Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1806 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Area Search | Area Search Scenario | 18 | Jun 5, 2026 | ||
| Search | Simulated Search Environment | 18 | Jun 5, 2026 | ||
| Blur Prediction | Radiographs SOD 24.8mm | 18 | Jun 5, 2026 | ||
| Scientific Reasoning | SciKnowEval L3 | 18 | Jun 4, 2026 | ||
| Graph Classification | PascalVOC-SP (test) | 18 | Jun 4, 2026 | ||
| Graph Classification | COCO-SP (test) | 18 | Jun 4, 2026 | ||
| Node Classification | Roman-empire | 18 | Jun 4, 2026 | ||
| Node Classification | Questions | 18 | Jun 4, 2026 | ||
| Node Classification | Questions | 18 | Jun 4, 2026 | ||
| Anomaly Detection | HDFS | 18 | Jun 9, 2026 | ||
| Object Recognition | Office-31 | 18 | Jun 4, 2026 | ||
| Landmark Detection | Shenzhen (test) | 18 | Jun 4, 2026 | ||
| Person understanding and persistent memory | CUPID | 18 | Jun 4, 2026 | ||
| Person understanding and persistent memory | RealPref | 18 | Jun 4, 2026 | ||
| Person understanding and persistent memory | KnowMe | 18 | Jun 4, 2026 | ||
| Downstream Evaluation | SEA-HELM | 18 | Jun 4, 2026 | ||
| Collaborative 3D Object Detection | OPV2V-H (test) | 18 | Jun 4, 2026 | ||
| Collaborative 3D Object Detection | V2X-Real (test) | 18 | Jun 4, 2026 | ||
| Multi-hop Question Answering | Bamboogle out-of-domain | 18 | Jun 4, 2026 | ||
| Multi-hop Question Answering | MuSiQue (out-of-domain) | 18 | Jun 4, 2026 | ||
| Question Answering | PopQA out-of-domain | 18 | Jun 4, 2026 | ||
| Image Captioning | COCO full (val) | 18 | Jun 4, 2026 | ||
| Visual Question Answering | OK-VQA full (val) | 18 | Jun 4, 2026 | ||
| Time Series Forecasting | Beijing PM2.5 (test) | 18 | Jun 4, 2026 | ||
| Clustering | CCV20 | 18 | Jun 4, 2026 |