Unverified50% confidenceBenchmarkExact time
阿里千问代码生成准确率据称达到94.7%，较上一代提升约11个百分点
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/25/2026
First Seen
Valid until: 10/23/2026
Sources
中国开源大模型如何逼近美国闭源巨头？
Related Claims
Unverified阿里千问新一代模型参数达2.4万亿，是该系列首个突破万亿的多模态大模型，代码生成准确率据称达到94.7%，较上一代提升约11个百分点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)