Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1253 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Sentiment Analysis | MultiMM CN (test) | 24 | Feb 26, 2026 | ||
| Sentiment Analysis | MultiMM EN (test) | 24 | Feb 26, 2026 | ||
| Metaphor Detection | MultiMM CN (test) | 24 | Feb 26, 2026 | ||
| Metaphor Detection | MultiMM EN (test) | 24 | Feb 26, 2026 | ||
| Tabular Understanding | TableGPT | 24 | Feb 26, 2026 | ||
| Table Summarization | QTSumm | 24 | Feb 26, 2026 | ||
| Table-to-Text Generation | FeTaQA | 24 | Feb 26, 2026 | ||
| Table Reasoning | InfoTabs | 24 | Feb 26, 2026 | ||
| Table Question Answering | TabMCQ | 24 | Feb 26, 2026 | ||
| LUMO property prediction | QM9 (test) | 24 | Feb 26, 2026 | ||
| HOMO property prediction | QM9 (test) | 24 | Feb 26, 2026 | ||
| Node-level classification | ROMAN EMP. | 24 | Feb 26, 2026 | ||
| Multi-hop document retrieval | HotpotQA (test) | 24 | Jun 16, 2026 | ||
| Multi-hop document retrieval | Musique (test) | 24 | May 22, 2026 | ||
| Preference Profile Estimation | Summary | 24 | Feb 26, 2026 | ||
| Preference Profile Estimation | Assistant | 24 | Feb 26, 2026 | ||
| Mathematical Reasoning | Mathematical Reasoning Suite MathQA, GSM8K, AddSub, SingleEq, SVAMP | 24 | Feb 26, 2026 | ||
| Triplet Alignment | AG-News | 24 | May 28, 2026 | ||
| Offline Promptable Video Segmentation | ES, PU, LV, and SV (Offline) | 24 | Feb 26, 2026 | ||
| POS tagging | UD Treebank English 2.15 | 24 | Feb 26, 2026 | ||
| POS tagging | UD Treebank Dutch 2.15 | 24 | Feb 26, 2026 | ||
| Code Generation | MBPP+ | 24 | Feb 26, 2026 | ||
| Mathematical Reasoning | GSM8K (test) | 24 | Feb 26, 2026 | ||
| Reasoning | Sonnet Writing | 24 | Feb 26, 2026 | ||
| Reasoning | Python Puzzles | 24 | Feb 26, 2026 |