Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1392 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Reward Modeling | HREF | 22 | Feb 26, 2026 | ||
| Reward Modeling | SCAN HPD | 22 | Feb 26, 2026 | ||
| Reward Modeling | Reward Bench V2 | 22 | Feb 26, 2026 | ||
| Reward Modeling | JudgeBench | 22 | May 19, 2026 | ||
| Knowledge Graph Question Answering | MetaQA 3-hop | 22 | May 25, 2026 | ||
| Fine-grained Named Entity Recognition | SampurNER | 22 | Feb 26, 2026 | ||
| Question Answering | GPQA | 22 | Mar 12, 2026 | ||
| Long-context Question Answering | FRAMES | 22 | Feb 26, 2026 | ||
| Hate speech classification and explainability | HateXplain (test) | 22 | Feb 26, 2026 | ||
| Multimodal Sentiment Analysis | CMU-MOSEI segments (test) | 22 | Feb 26, 2026 | ||
| Multimodal Sentiment Analysis | CMU-MOSI segments (test) | 22 | Feb 26, 2026 | ||
| Document Machine Translation | EN-ZH | 22 | Feb 26, 2026 | ||
| Document-level Machine Translation | EN-ZH standard (test) | 22 | Feb 26, 2026 | ||
| Machine Translation | WMT En-Zh 2023 (test) | 22 | Feb 26, 2026 | ||
| Question Answering | GAIA | 22 | May 25, 2026 | ||
| Relational Triplet Extraction | Wiki-NRE | 22 | Feb 26, 2026 | ||
| Relational Triplet Extraction | REBEL | 22 | Feb 26, 2026 | ||
| Mathematical Reasoning | GSM8K (train) | 22 | Feb 26, 2026 | ||
| Text Classification | Emotion | 22 | May 29, 2026 | ||
| Web-based Question Answering | BrowseComp-plus | 22 | May 27, 2026 | ||
| Text Segmentation | arXiv | 22 | Mar 24, 2026 | ||
| Mathematical Reasoning | Minerva | 22 | Feb 26, 2026 | ||
| Mathematical Word Problem Solving | GSM8K | 22 | May 14, 2026 | ||
| Speech-to-Speech Question-Answering | TriviaQA | 22 | Apr 21, 2026 | ||
| AutoEncoding | Mathematical expressions EVAL (test) | 22 | Feb 26, 2026 |