Unverified50% confidenceFactExact time
Vertical benchmarks include HumanEval/MBPP (code), MATH/GSM8K (mathematical reasoning), and MMLU (multidisciplinary knowledge).
1
Sources
50%
Confidence
Long-term
Relevance
9/24/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedDeepSpec配套九个评测基准，涵盖数学推理（GSM8K、MATH-500）、代码生成（HumanEval、MBPP、LiveCodeBench）和通用对话（MT-Bench、Alpaca、Arena-Hard v2）72% similarUnverifiedCommon sub-benchmarks included in composite intelligence indices are MMLU, HumanEval, MBPP, MATH, GSM8K, GPQA, and LongBench.71% similarUnverifiedDeepSeek Coder以DeepSeek Math为底层基础，DeepSeek Math在MATH、GSM8K等数学基准上表现优异59% similarUnverifiedDeepSeek-Coder-V2 has long ranked among the top on code evaluation leaderboards such as HumanEval.59% similarUnverified技术栈层次为：DeepAgent基于Agent，Agent底层是LangGraph，LangGraph驱动LLM59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/947545API
curl https://kongchang.com/api/v1/knowledge/claims/947545MCP
get_claim(id=947545)