Unverified50% confidenceBenchmarkExact time

DeepSeek Coder在HumanEval、MBPP等代码基准测试上表现接近同参数规模的商业模型，且对中文注释场景理解能力更优

1

Sources

50%

Confidence

Medium-term (~90 days)

Relevance

7/7/2026

First Seen

Valid until: 10/5/2026

Sources

Codex配置实战：国内低成本接入GPT-5.5完整教程

bilibilidream黎6/7/2026

Related Claims

UnverifiedDeepSeek-Coder performs excellently on mainstream code evaluation benchmarks like HumanEval and MBPP.76% similar UnverifiedDeepSeek-Coder在多项编程基准测试中达到国际领先水平74% similar VerifiedDeepSeek在多项代码基准测试（如HumanEval、MBPP、LiveCodeBench）中表现优异，部分指标接近甚至超越GPT-4级别模型73% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/164774

API

curl https://kongchang.com/api/v1/knowledge/claims/164774

MCP

get_claim(id=164774)