Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 1927 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Medical Question Answering | Medical Benchmarks (MedQA, MedMCQA, BULLET) (test) | 18 | Feb 26, 2026 | ||
| Agent Memory Retrieval | LoCoMo (test) | 18 | Feb 26, 2026 | ||
| Agent Memory Question Answering | PerLTQA (test) | 18 | Feb 26, 2026 | ||
| Logical Reasoning | LRLs Bengali Swahili Telugu | 18 | Feb 26, 2026 | ||
| Logical Reasoning | HRLs (High-Resource Languages: French, Spanish, Italian, German, Russian, Chinese) | 18 | Feb 26, 2026 | ||
| Deep research | BrowseComp-zh | 18 | Feb 26, 2026 | ||
| Omnimodal Question Answering | OmniVideoBench 1.0 (test) | 18 | Feb 26, 2026 | ||
| Long Audio-Video Question Answering | WorldSense | 18 | Feb 26, 2026 | ||
| Mathematical Reasoning | Math-500 | 18 | Mar 19, 2026 | ||
| Mathematical Reasoning | TheoremQA | 18 | Feb 26, 2026 | ||
| Mathematical Reasoning | OlympiadBench Math | 18 | Feb 26, 2026 | ||
| Mathematical Reasoning | AIME 2024 (val) | 18 | Apr 14, 2026 | ||
| Long-context understanding | LongBench | 18 | Feb 26, 2026 | ||
| Safety Detection | Polyguard Social Media | 18 | Feb 26, 2026 | ||
| Safety Detection | Polyguard HR | 18 | Feb 26, 2026 | ||
| Safety Detection | Polyguard Education | 18 | Feb 26, 2026 | ||
| Safety Detection | Polyguard Cyber | 18 | Feb 26, 2026 | ||
| Safety Detection | Polyguard Code | 18 | Feb 26, 2026 | ||
| Overrefusal Detection | OR-Bench | 18 | Feb 26, 2026 | ||
| Audio-visual Question Answering | video-SALMONN 2 (test) | 18 | Feb 26, 2026 | ||
| Audio-visual Question Answering | OmniVideoBench | 18 | Feb 26, 2026 | ||
| Audio-visual Question Answering | WorldSense | 18 | Feb 26, 2026 | ||
| Mathematical Reasoning | MATH500 | 18 | Feb 26, 2026 | ||
| Mathematical Reasoning | AIME24 | 18 | Mar 24, 2026 | ||
| Relation Extraction | CAIL 2022 | 18 | Feb 26, 2026 |