Benchmark
HARDMath2 Benchmark
What is HARDMath2?
HARDMath2 is a benchmark for applied mathematics created by students in a graduate class at Harvard University, featuring 211 original problems covering core…
- Released
- 2025-05-17
- Evaluates
- 推理, Reasoning, 代码, Code, 数学, Math, Strong Reasoning, 大语言模型, LLM, 逻辑推理, 代码工程, 数理能力, 不支持, Unsupported
- Openness
- unknown
- Importer
- OpenCompass Hub
- Reported scores
- 0
Source provenance
- Original evidence https://hub.opencompass.org.cn/dataset-detail/HARDMath2
HARDMath2 paper and dataset
No reported scores are on record for this benchmark yet.