Research
Benchmarks
Compare state-of-the-art methods across the tasks and datasets used to measure AI progress.
309,131 benchmarksPage 736 of 12,366
Benchmarks
| Task | Dataset | Domain | Trend | Results | Last update |
|---|---|---|---|---|---|
| Coreference Resolution | CoreRes | 33 | Feb 26, 2026 | ||
| Multi-turn Dialogue | MTBench101 | 33 | Feb 26, 2026 | ||
| Multi-discipline Understanding | MMLU | 33 | Mar 31, 2026 | ||
| Question Answering | HotPotQA | 33 | Mar 13, 2026 | ||
| Semantic Textual Similarity | SICK Slovak (val) | 33 | Feb 26, 2026 | ||
| Semantic Textual Similarity | STS Benchmark Slovak (val) | 33 | Feb 26, 2026 | ||
| Syntactic Parsing | SpokeBench 1.0 (test) | 33 | Feb 26, 2026 | ||
| Summarization | MultiNews LongBench (test) | 33 | May 22, 2026 | ||
| Degradation Estimation | HUST | 33 | Feb 26, 2026 | ||
| Degradation Estimation | XJTU-SY | 33 | Feb 26, 2026 | ||
| Degradation Estimation | PRONOSTIA | 33 | Feb 26, 2026 | ||
| Lane-Keeping Trajectory Prediction | Udacity Simulator | 33 | Feb 26, 2026 | ||
| Lane-Keeping Action Classification | OpenAI CarRacing | 33 | Feb 26, 2026 | ||
| Irregular Time-Series Classification | PAR | 33 | Feb 26, 2026 | ||
| Multilingual Medical Reasoning | CUREMED-BENCH (test) | 33 | Feb 26, 2026 | ||
| Mathematical Reasoning | GSM8K standard (test) | 33 | Jun 23, 2026 | ||
| Security Evaluation | SecEval | 33 | Jul 3, 2026 | ||
| Windows UI Navigation | WindowsAgentArena (WAA) | 33 | May 29, 2026 | ||
| General Question Answering | TriviaQA out-of-domain (val test) | 33 | Jun 4, 2026 | ||
| Coding | LiveCodeBench v5 | 33 | Jun 26, 2026 | ||
| GUI Grounding | ScreenSpot v2 (test) | 33 | Jun 15, 2026 | ||
| Mathematical Reasoning | AIME 2025 | 33 | Feb 26, 2026 | ||
| Mathematical Reasoning | MATH 500 | 33 | Feb 26, 2026 | ||
| Mathematical Reasoning | AIME 2024 | 33 | Feb 26, 2026 | ||
| Language Understanding | MMLU | 33 | Feb 26, 2026 |