Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 106 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Perplexity | WikiText-2 | 113 | Jun 24, 2026 | ||
| Multi-modal Understanding | MMBench EN | 113 | Jun 9, 2026 | ||
| Mathematical Problem Solving | AIME 2024 | 113 | Apr 30, 2026 | ||
| Text Embedding | MTEB English v2 | 113 | Jul 7, 2026 | ||
| Long-context Reasoning | LongBench v2 | 113 | Jul 3, 2026 | ||
| Mathematical Reasoning | AIME 24 | 113 | Feb 26, 2026 | ||
| Reasoning | ARC-c | 113 | Jul 2, 2026 | ||
| Question Answering | 2WikiMultihopQA (test) | 113 | May 29, 2026 | ||
| Open Vocabulary Semantic Segmentation | Pascal VOC 20 | 113 | May 26, 2026 | ||
| Novel View Synthesis | ACID (test) | 113 | Jul 7, 2026 | ||
| Video Question Answering | LongVideoBench (val) | 113 | Jun 12, 2026 | ||
| Base-to-New Generalization | ImageNet | 113 | Jul 2, 2026 | ||
| Node Classification | Minesweeper | 113 | May 21, 2026 | ||
| Time Series Forecasting | ECL (test) | 113 | Jun 1, 2026 | ||
| Subject-driven Image Generation | DreamBench | 113 | May 26, 2026 | ||
| Fake News Detection | Gossipcop | 113 | Jun 9, 2026 | ||
| Language Modeling | GitHub (test) | 113 | Feb 26, 2026 | ||
| Image Classification | CIFAR-100 non-IID (test) | 113 | Mar 17, 2026 | ||
| Image Classification | ImageNet Rendition | 113 | May 29, 2026 | ||
| Image Classification | ImageNet 1K (train val) | 113 | May 19, 2026 | ||
| Few-Shot Classification | mini-ImageNet (test) | 113 | Feb 26, 2026 | ||
| Graph classification | MNIST | 113 | Jun 26, 2026 | ||
| Out-of-Distribution Detection | ImageNet | 113 | Apr 24, 2026 | ||
| Node Classification | ogbn-proteins | 113 | May 26, 2026 | ||
| Video Grounding | Charades-STA | 113 | Jun 16, 2026 |