Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1202 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Session-based Recommendation | Book | 24 | Apr 16, 2026 | ||
| Session-based Recommendation | Yelp | 24 | Apr 16, 2026 | ||
| Session-based Recommendation | Beauty | 24 | Apr 16, 2026 | ||
| Wrench Forecasting | RH20T (test) | 24 | Apr 15, 2026 | ||
| Membership Inference Attack | Challenge Set (third-party evaluation) | 24 | Apr 15, 2026 | ||
| Document Ranking | TREC Robust | 24 | Apr 15, 2026 | ||
| Document Ranking | MS MARCO Document | 24 | Apr 15, 2026 | ||
| Document Ranking | MS MARCO Passage | 24 | Apr 15, 2026 | ||
| Continual Unlearning | CIFAR-100 ResNet-20 (test) | 24 | Apr 15, 2026 | ||
| Knowledge Base Question Answering | WebQuestion | 24 | Apr 15, 2026 | ||
| Image-Text Retrieval | COCO 1.0 (test) | 24 | Apr 15, 2026 | ||
| Image Classification | VTAB+ 1.0 (test) | 24 | Apr 15, 2026 | ||
| Image Classification | ImageNet-1K 1.0 (test) | 24 | Apr 15, 2026 | ||
| Problem Solving | List Function (test) | 24 | Apr 15, 2026 | ||
| Multi-turn dialogue | ShareGPT, JDDC, and MedDG Aggregated | 24 | Apr 15, 2026 | ||
| Multi-turn dialogue | MedDG | 24 | Apr 15, 2026 | ||
| Multi-turn dialogue | JDDC | 24 | Apr 15, 2026 | ||
| Multi-turn dialogue | ShareGPT | 24 | Apr 15, 2026 | ||
| Spreadsheet Understanding and Manipulation | SpreadsheetBench Soft Restriction | 24 | Apr 15, 2026 | ||
| Model Accuracy | Model Utility Evaluation Set | 24 | Apr 15, 2026 | ||
| Text-to-Image Generation | OneIG-Bench EN | 24 | Apr 15, 2026 | ||
| Least-squares Optimization | Least-squares Optimization (test) | 24 | Apr 15, 2026 | ||
| Consensus Optimization | Consensus Optimization (test) | 24 | Apr 15, 2026 | ||
| Long-horizon agentic task | BrowseComp-Plus | 24 | Apr 14, 2026 | ||
| Long-horizon agentic task | BrowseComp | 24 | Apr 14, 2026 |