Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1128 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Time Series Forecasting | Weather | 25 | Feb 27, 2026 | ||
| LLM Unlearning | TOFU 5% (forget set) | 25 | Feb 26, 2026 | ||
| Differentially Private Model Training | DP Noise Correlation Utility | 25 | Feb 26, 2026 | ||
| Math Reasoning | GSM8K | 25 | Jul 3, 2026 | ||
| Question Answering | OpenBookQA published (test) | 25 | Jun 4, 2026 | ||
| Regression | Concrete | 25 | Feb 26, 2026 | ||
| MAP Inference | PATH | 25 | Feb 26, 2026 | ||
| MAP Inference | SNOW-dataset | 25 | Feb 26, 2026 | ||
| MAP Inference | STAR-dataset | 25 | Feb 26, 2026 | ||
| Biological Sequence Generation | MPRA | 25 | Feb 26, 2026 | ||
| Molecular Generation | ZINC250K | 25 | Feb 26, 2026 | ||
| Molecular Generation | QM9 | 25 | Feb 26, 2026 | ||
| Traveling Salesman Problem | TSP-50 | 25 | Apr 23, 2026 | ||
| LLM Safety | Safety Evaluation Set | 25 | Feb 26, 2026 | ||
| Collaborative Filtering | Yelp | 25 | Feb 26, 2026 | ||
| Structural Complexity Ground Truth Prediction | 96 datasets | 25 | Feb 26, 2026 | ||
| Video Understanding | VideoMME Long | 25 | Feb 26, 2026 | ||
| Autonomous Driving Planning | WOD-E2E (test) | 25 | May 25, 2026 | ||
| Spatial Aesthetic Image Quality Assessment | SA-BENCH | 25 | Feb 26, 2026 | ||
| Video Understanding | Average VideoMME, LongVideoBench, MLVU | 25 | Feb 27, 2026 | ||
| Semantic Segmentation | Pascal VOC high-quality (test) | 25 | Feb 26, 2026 | ||
| Depth Estimation | ETH3D | 25 | Apr 24, 2026 | ||
| Virtual Try-On | DressCode Dresses (unpaired) | 25 | Jul 1, 2026 | ||
| Aggregate Multimodal Evaluation | Aggregate | 25 | Feb 26, 2026 | ||
| Multimodal Understanding | SEED | 25 | Jun 5, 2026 |