Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1494 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Masked Entity Prediction | ICEWS18 standard (test) | 21 | Feb 26, 2026 | ||
| Multi-discipline reasoning | MMMU-Pro | 21 | Mar 16, 2026 | ||
| Scientific Reasoning | MMLU Pro (test) | 21 | Mar 4, 2026 | ||
| Communication Overhead | TinyImageNet (test) | 21 | Feb 26, 2026 | ||
| Communication Overhead | CIFAR-100 (test) | 21 | Feb 26, 2026 | ||
| Communication Overhead | CIFAR-10 (test) | 21 | Feb 26, 2026 | ||
| Multi-label Classification | CheXpert | 21 | Feb 26, 2026 | ||
| Visual Grounded Reasoning | HR-Bench-8K | 21 | Mar 6, 2026 | ||
| Visual Grounded Reasoning | HR-Bench-4K | 21 | Mar 6, 2026 | ||
| Skeleton-based Action Recognition | NTU RGB+D (X-Sub) | 21 | Feb 26, 2026 | ||
| Multi-modal Retrieval (Image Query) | WebQA | 21 | Feb 27, 2026 | ||
| Multi-modal Retrieval (Text Query) | WebQA | 21 | Feb 27, 2026 | ||
| Multi-modal Retrieval (Image Query) | MMQA | 21 | Feb 27, 2026 | ||
| Multi-modal Retrieval (Text Query) | MMQA | 21 | Feb 27, 2026 | ||
| Multi-label content safety classification | Synthetic Dataset | 21 | Feb 26, 2026 | ||
| OCR-based Visual Question Answering | AI2D 2016 (test) | 21 | Feb 26, 2026 | ||
| Information Retrieval | DBPedia BEIR (test) | 21 | Apr 13, 2026 | ||
| Text Clustering | Aggregate | 21 | Feb 26, 2026 | ||
| Text Clustering | Yah B | 21 | Feb 26, 2026 | ||
| Text Clustering | Yah(F) | 21 | Feb 26, 2026 | ||
| Multi-Image Understanding | MuirBench (test) | 21 | Feb 26, 2026 | ||
| Multilingual Commonsense Reasoning | M-Hellaswag | 21 | Feb 26, 2026 | ||
| Toxicity Detection | HateXplain | 21 | Feb 26, 2026 | ||
| Event Argument Extraction | ACE 2005 | 21 | Apr 14, 2026 | ||
| Closed QA | Coverage (test) | 21 | Feb 26, 2026 |