Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2715 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Image Classification | CIFAR-10 (test) | 14 | Mar 16, 2026 | ||
| Streaming Video Reasoning | StreamingBench Real-Time | 14 | Mar 16, 2026 | ||
| Non-isometric Shape Matching | DT4D-H intra | 14 | Mar 16, 2026 | ||
| Design Optimization | 10 optimization shared-core domains | 14 | Mar 16, 2026 | ||
| Intent Classification | Intent (test) | 14 | Mar 16, 2026 | ||
| General Language Understanding | 8 Sub-Tasks (test) | 14 | Mar 16, 2026 | ||
| Utility | POPE | 14 | Mar 16, 2026 | ||
| Utility | MME | 14 | Mar 16, 2026 | ||
| Utility | ScienceQA | 14 | Mar 16, 2026 | ||
| Safety | MLLMGuard | 14 | Mar 16, 2026 | ||
| Safety | PrivacyPair (test) | 14 | Mar 16, 2026 | ||
| Visual Document Retrieval | ViDoRe 8 datasets v3 | 14 | Mar 16, 2026 | ||
| Visual Document Retrieval | ViDoRe 10 datasets v1 | 14 | Mar 16, 2026 | ||
| Salient Object Detection | EORSSD, ORSSD, and ORSI-4199 (test) | 14 | Mar 16, 2026 | ||
| Video Generation | WorldArena | 14 | May 8, 2026 | ||
| Time Series Forecasting | CAF-7M EASY | 14 | Mar 16, 2026 | ||
| Time Series Forecasting | CAF-7M HARD | 14 | Mar 16, 2026 | ||
| Time Series Forecasting | CAF-7M (ALL) | 14 | Mar 16, 2026 | ||
| Mobile UI Automation | AndroidControl High (test) | 14 | Mar 16, 2026 | ||
| Graph Classification | DrugOOD assay | 14 | Mar 16, 2026 | ||
| Graph Classification | GOOD-Twitter length | 14 | Mar 16, 2026 | ||
| Text-to-Image Generation | UniGenBench++ Long | 14 | Mar 13, 2026 | ||
| Text-to-Image Generation | UniGenBench++ Short | 14 | Mar 13, 2026 | ||
| Behavioral Dialogue Evaluation | LifeSim (test) | 14 | Mar 13, 2026 | ||
| Personalized Assistant Interaction | LifeSim-Eval Single-Scenario | 14 | Mar 13, 2026 |