Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 88 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Proactive recommendation | ProPerSim Day 1 1.0 (test) | 128 | Feb 26, 2026 | ||
| Utility Assessment | AgentDojo (test) | 128 | Feb 26, 2026 | ||
| Forecasting | Icentia | 128 | Feb 27, 2026 | ||
| Video Understanding | LongVideoBench | 128 | Jul 7, 2026 | ||
| Machine Translation | FLORES+ (test) | 128 | Feb 26, 2026 | ||
| Long-term memory evaluation | LoCoMo | 128 | Jun 2, 2026 | ||
| Multi-Hop Question Answering | Bamboogle | 128 | Apr 10, 2026 | ||
| Image Classification | ImageNet (val) | 128 | Feb 26, 2026 | ||
| Emotion Classification | Emotion Classification In-domain (test) | 128 | Feb 26, 2026 | ||
| Node classification | Tolokers (test) | 128 | May 27, 2026 | ||
| Topic Classification | AG News (test) | 128 | Jun 4, 2026 | ||
| Action Recognition | NW-UCLA | 128 | May 22, 2026 | ||
| Node Classification | ogbn-products | 128 | Jun 2, 2026 | ||
| Out-of-Distribution Detection | Texture | 128 | May 27, 2026 | ||
| Graph Classification | MNIST (test) | 128 | Jul 1, 2026 | ||
| Graph classification | CIFAR10 | 128 | Jun 26, 2026 | ||
| Visual Object Tracking | NFS | 128 | May 12, 2026 | ||
| Few-Shot Class-Incremental Learning | CUB200 (test) | 128 | Jun 24, 2026 | ||
| Image Retrieval | MS-COCO 1K (test) | 128 | Feb 26, 2026 | ||
| Visual Question Answering | VQA-CP v2 (test) | 128 | Mar 24, 2026 | ||
| Character-level Language Modeling | text8 (test) | 128 | Feb 26, 2026 | ||
| Relation Classification | SemEval-2010 Task 8 (test) | 128 | Feb 26, 2026 | ||
| Image Classification | Food (test) | 128 | Apr 28, 2026 | ||
| Image Classification | Places-LT (test) | 128 | Feb 26, 2026 | ||
| Hallucination Detection | SQuAD | 127 | Jun 23, 2026 |