Unverified50% confidenceFactExact time
Gemini 3.1 Pro High在Sonar评估中综合质量最优，代码简洁度较好，圈复杂度为234
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026
Sources
Sonar实测53个大模型代码质量：Claude安全漏洞最多，GPT-5代码量暴增5倍
bilibiliAI_Express6/1/2026
Related Claims
UnverifiedGemini 3.1 Pro High在SWE-bench测试中通过率为84.17%，排名第一，生成代码量为307,000行，Bug密度为614个/百万行代码，安全问题为210个/百万行代码72% similarUnverifiedGemini Pro/Ultra系列在复杂推理、大规模代码分析方面表现更优71% similarUnverifiedGemini 3.1 Pro High showed the most balanced performance and is described as the best overall quality choice among evaluated models68% similarUnverified用户认为Gemini 3.1 Pro的回复高度可读、内容组织清晰、逻辑层次分明68% similarUnverifiedGemini 3.5 Pro在ARC-AGI-2通用智能评估中得分42分，远超同期竞品65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/51219API
curl https://kongchang.com/api/v1/knowledge/claims/51219MCP
get_claim(id=51219)