Expired50% confidenceFactExact time
Domestic large models such as ByteDance's Doubao series, Alibaba's Qwen (Tongyi Qianwen), and DeepSeek's DeepSeek-Coder have approached or even reached the international top tier on code benchmark tests such as HumanEval and MBPP.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026(expired)
Sources
Related Claims
UnverifiedDeepSeek-Coder在多项编程基准测试中达到国际领先水平70% similarUnverifiedDomestic models such as Alibaba's Tongyi Qianwen (Qwen), DeepSeek, and Zhipu GLM have approached the international top tier in Chinese language understanding and generation.69% similarUnverifiedIn domestic mainstream large model programming capability tests, Zhipu GLM ranks first, while DeepSeek, Kimi, and MiniMax are in the second tier, and Alibaba Tongyi and Tencent Hunyuan perform slightly worse.69% similarUnverifiedDeepSeek Coder performs close to commercial models of the same parameter scale on code benchmarks such as HumanEval and MBPP, and has superior comprehension of Chinese annotation scenarios.68% 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68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/40874API
curl https://kongchang.com/api/v1/knowledge/claims/40874MCP
get_claim(id=40874)