Unverified50% confidenceFactExact time
MMLU评估模型在57个学科领域的知识广度，HumanEval测量代码生成正确率，GSM8K考察数学推理，HELM构建综合多维评估框架
1
Sources
50%
Confidence
Long-term
Relevance
7/15/2026
First Seen
Sources
Related Claims
UnverifiedMMLU涵盖57个学科领域的57000余道选择题，HumanEval专注于代码生成的函数级正确性验证80% similarVerified主流大模型评测基准包括 MMLU、HumanEval/SWE-bench、MATH、GPQA 等79% similarUnverified主流AI基准测试如MMLU、HumanEval、GSM8K主要评估知识问答、代码生成和数学推理能力，尚无成熟框架能评估模型在情感真实性上的表现78% similarUnverifiedAI模型基准测试通常在MMLU、HumanEval、GSM8K等标准数据集上评估模型的推理、编码和数学能力78% similarUnverified主流 LLM 能力评测体系包括 MMLU、HumanEval、GSM8K 等标准化基准77% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/515969API
curl https://kongchang.com/api/v1/knowledge/claims/515969MCP
get_claim(id=515969)