Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 2273 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Question Answering | 50-question climate adaptation dataset 1.0 (test) | 16 | Feb 26, 2026 | ||
| Coding | LiveCodeBench | 16 | Feb 26, 2026 | ||
| General Reasoning | Global MMLU | 16 | Feb 26, 2026 | ||
| Summarization | XL-SUM Target language | 16 | Feb 26, 2026 | ||
| Machine Translation | FLORES-200 Target language | 16 | Feb 26, 2026 | ||
| Machine Reading Comprehension | Belebele Source language en | 16 | Feb 26, 2026 | ||
| Summarization | XL-SUM en | 16 | Feb 26, 2026 | ||
| Machine Translation | FLORES-200 Source language en | 16 | Feb 26, 2026 | ||
| Mathematical Reasoning | MATH 500 | 16 | Feb 26, 2026 | ||
| Visual Reasoning | VisuLogic | 16 | Jun 2, 2026 | ||
| Long-context reasoning | BABILong | 16 | Jun 23, 2026 | ||
| Synthetic Reasoning | Reasoning Primitives | 16 | Feb 26, 2026 | ||
| Mathematical Reasoning | Math Word | 16 | Feb 26, 2026 | ||
| Multi-subject Knowledge | MMLU | 16 | May 13, 2026 | ||
| Relation Extraction | FewRel (test) | 16 | Feb 27, 2026 | ||
| Relation Extraction | Wiki ZSL (test) | 16 | Feb 27, 2026 | ||
| Multi-document Question Answering | MDQA | 16 | Feb 26, 2026 | ||
| Chat | AlpacaEval LC 2 | 16 | May 18, 2026 | ||
| Long-context Understanding | HELMET 2025 | 16 | Feb 26, 2026 | ||
| Continual Learning | SelfRC, TweetQA, and SST sequence SQuAD format (test) | 16 | Feb 26, 2026 | ||
| Code Generation | HumanEval 0-shot | 16 | May 1, 2026 | ||
| Knowledge Reasoning | GPQA Diamond | 16 | May 8, 2026 | ||
| Safety Evaluation | JailbreakBench | 16 | Apr 2, 2026 | ||
| End-to-end Translation | GLTL | 16 | Feb 26, 2026 | ||
| End-to-end Translation | CW | 16 | Feb 26, 2026 |