Unverified50% confidenceBenchmarkExact time
专为代码训练的模型（如DeepSeek-Coder系列）在代码基准上往往比同参数量的通用模型高出10-30个百分点
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/15/2026
First Seen
Valid until: 10/13/2026
Sources
Related Claims
Unverified初代 DeepSeek Math 基于 DeepSeek Coder 代码大模型进行预训练79% similarUnverifiedDeepSeek Coder和CodeLlama等专门针对代码优化的模型进一步降低了代码生成的错误率78% similarUnverifiedDeepSeek-Coder、CodeLlama等模型验证了专用编程模型路线的可行性，70B级专用模型可与规模更大的通用模型持平甚至超越77% similarVerifiedDeepSeek-Coder采用Fill-in-the-Middle（FIM）训练策略，使其擅长代码补全场景75% similarVerifiedDeepSeek-Coder在超过2万亿Token的代码和自然语言混合语料上进行预训练，支持超过80种编程语言74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/517562API
curl https://kongchang.com/api/v1/knowledge/claims/517562MCP
get_claim(id=517562)