Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 968 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Open-style response generation | Open-LLM Leaderboard | 28 | Feb 26, 2026 | ||
| Node Classification | Minesweeper v1 (test) | 28 | Feb 26, 2026 | ||
| Question Answering | NQ | 28 | Feb 26, 2026 | ||
| Question Answering | NQ (Natural Questions) | 28 | Feb 26, 2026 | ||
| Reasoning | Multi-Step Arithmetic | 28 | Feb 26, 2026 | ||
| Reasoning | StrategyQA (test) | 28 | Feb 26, 2026 | ||
| Natural Language Understanding | NusaX | 28 | Feb 26, 2026 | ||
| Question Answering | TyDiQA | 28 | Feb 26, 2026 | ||
| NSCLC segmentation | 4D-Lung (test) | 28 | Feb 26, 2026 | ||
| Language Modeling Downstream Evaluation | Downstream tasks Average (test) | 28 | Jun 16, 2026 | ||
| Mathematical problem solving | MathVerse (testmini) | 28 | Feb 26, 2026 | ||
| Streaming video understanding | OVOBench | 28 | Jul 2, 2026 | ||
| Short video understanding | MVBench | 28 | Apr 10, 2026 | ||
| Domain Adaptation | Office31 standard (test) | 28 | Feb 26, 2026 | ||
| Classification | ImageNet-shift | 28 | Jun 23, 2026 | ||
| Video Object Segmentation | YouTube-Objects | 28 | Feb 26, 2026 | ||
| Referring Video Object Segmentation | ReVOS Reasoning | 28 | May 26, 2026 | ||
| Code Generation | MBPP | 28 | Mar 17, 2026 | ||
| Person Re-identification | CCVID | 28 | Mar 31, 2026 | ||
| Multimodal Evaluation | SEED-Bench | 28 | Mar 9, 2026 | ||
| BEV segmentation (Vehicle) | nuScenes v1.0-trainval (val) | 28 | Feb 26, 2026 | ||
| Model Inversion Defense | CIFAR10 (val) | 28 | Feb 26, 2026 | ||
| Model Inversion Attack Defense | CIFAR100 (val) | 28 | Feb 26, 2026 | ||
| Image Classification Calibration | TinyImageNet | 28 | Apr 10, 2026 | ||
| Cognition and Reasoning | MMMU (val) | 28 | May 12, 2026 |