Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 703 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Jailbreak Defense | ActorAttack | 34 | Apr 3, 2026 | ||
| Time Series Classification | UEA 18 datasets 70% Missing | 34 | Apr 3, 2026 | ||
| Aspect-level Sentiment Analysis | COTE BD | 34 | Apr 2, 2026 | ||
| Optimization modeling | OptiBench | 34 | Jun 25, 2026 | ||
| Image Classification | ImageNet 1k (val) | 34 | Apr 1, 2026 | ||
| Attribution | WildDeepfake | 34 | May 13, 2026 | ||
| Binary classification | UNSW-NB15 | 34 | Jun 17, 2026 | ||
| Coverage Path Planning | 1,000 instances (test) | 34 | Mar 31, 2026 | ||
| Micro-Expression Recognition | IMER SLCV incremental learning stages (5 sessions) | 34 | Mar 31, 2026 | ||
| Visual Counting | PixMoCount (test) | 34 | Jun 2, 2026 | ||
| Safety Evaluation | WildChat | 34 | May 21, 2026 | ||
| Video Question Answering | MLVU (dev) | 34 | May 26, 2026 | ||
| Multimodal Event Forecasting | GDELT IMG-TXT | 34 | Mar 27, 2026 | ||
| Referring Expression Segmentation | RefCOCO UMD partition (test A) | 34 | May 28, 2026 | ||
| 3D Question Answering | SQA3D | 34 | Jun 2, 2026 | ||
| Anomaly Detection | MVTec AD | 34 | Apr 23, 2026 | ||
| Group Assignment | RadTimeline (test) | 34 | Mar 25, 2026 | ||
| Medical Visual Question Answering | Federated Medical VQA Mixed-Modality Task 3 VQA-Med 2019-2021 SLAKE VQA-RAD (test) | 34 | Mar 24, 2026 | ||
| Road segmentation | CHN6-CUG | 34 | Apr 20, 2026 | ||
| Code Generation | HumanEval+ | 34 | May 28, 2026 | ||
| Few-shot segmentation | ISIC | 34 | Jul 1, 2026 | ||
| Question Answering | MMLU Med | 34 | Apr 29, 2026 | ||
| 3D shape matching | SCAPE original (test) | 34 | Mar 20, 2026 | ||
| 3D shape matching | FAUST original (test) | 34 | Mar 20, 2026 | ||
| Image Classification | Caltech-256 | 34 | Mar 20, 2026 |