Unverified50% confidenceFactExact time
This evaluation uses the national college entrance examination (Gaokao) mathematics Paper 1 as the benchmark, with a dataset comprising 14 questions.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
8/18/2026
First Seen
Valid until: 11/16/2026
Sources
Related Claims
Unverified评测数据集为JSONLines格式，包含14道高考数学客观题，数学公式采用LaTeX格式，每个模型运行三次65% similarUnverified代码、SQL、数学计算等有标准答案的场景应使用代码断言评测，以单元测试是否全量通过作为成功判定，客观性最强60% similarUnverified锚定样本技术在评估提示词中加入已由人类专家标注明确分数的示例，覆盖评分量表各个档位，可帮助裁判模型准确理解评分标准59% similarUnverifiedThe tested task was conducted over four rounds, dispatching a cumulative total of 68 sub-agents to complete batch prompt testing for a digital human writing skills module.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/771366API
curl https://kongchang.com/api/v1/knowledge/claims/771366MCP
get_claim(id=771366)