[KongchangAI]
Verified80% confidenceFactTime unknown

DeepSeek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

20
Sources
80%
Confidence
Medium-term (~90 days)
Relevance
6/1/2026
First Seen
Valid until: 8/30/2026

Sources

Codex接入DeepSeek教程：中转脚本三步搞定
bilibili王了小王

Related Entities

DeepSeekcompanyHumanEvalconceptMBPPconceptLiveCodeBenchconceptGPT-4model

Related Claims

UnverifiedDeepSeek-Coder performs excellently on mainstream code evaluation benchmarks like HumanEval and MBPP.77% similarUnverifiedDeepSeek的代码能力在多项基准测试中达到国际领先水平77% similar

Cite This Claim

Stable URI
https://kongchang.com/claim/19606
API
curl https://kongchang.com/api/v1/knowledge/claims/19606
MCP
get_claim(id=19606)