Expired50% confidenceBenchmarkExact time
Alibaba Qwen's code generation accuracy is reportedly 94.7%, an improvement of approximately 11 percentage points over the previous generation.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/25/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/23/2026(expired)
Sources
中国开源大模型如何逼近美国闭源巨头？
Related Claims
UnverifiedAlibaba's new-generation Qianwen model has 2.4 trillion parameters, making it the first multimodal large model in the series to exceed one trillion parameters; its code generation accuracy is reportedly 94.7%, an improvement of approximately 11 percentage points over the previous generation.72% similarUnverifiedEven the most advanced code generation models achieve a functional correctness rate of only 60%–80% for generated code, while the models' confidence in the correctness of their own output is often as high as 90% or more.70% similarUnverifiedAfter using the AI debugging trio template (complete error message + relevant code snippet + expected behavior), the answer accuracy rate increased from 30% to over 90%, and problems were essentially resolved in a single attempt.67% similarUnverifiedAI intent recognition accuracy generally falls between 85% and 95%.65% similarUnverified即便单字符识别准确率达到99%，对于一个包含10个字符的字段，其整体正确率也仅约90%，这被称为"准确率衰减效应"65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/613808API
curl https://kongchang.com/api/v1/knowledge/claims/613808MCP
get_claim(id=613808)