Expired90% confidenceFactTime unknown
Gemini 3.5 Flash在几乎所有基准测试中超越了Gemini 3.1 Pro
19
Sources
90%
Confidence
Medium-term (~90 days)
Relevance
5/31/2026
First Seen
Valid until: 8/29/2026(expired)
Sources
Gemini 3.5 Flash深度翻车:跑分亮眼实战拉胯,CLI工具千疮百孔
bilibili量子菠萝_
Related Entities
Related Claims
UnverifiedGemini 3.5 Flash的编码能力基准测试得分为76.2%82% similarUnverified科技博主Theo在实战编码测试中发现Gemini 3.5 Flash是所有测试模型中唯一一个没能让游戏正常运行的82% similarUnverifiedGemini 3 Flash在生成收音机前控制面板SVG时,细节表现不如Gemini 3 Pro82% similarUnverifiedGemini 3.5 Flash在Agent任务基准测试中获得83.6%的得分81% similarUnverifiedStep 3.5 Flash在编码测试(如SWE-Bench)等特定基准测试中分数超越了Google的Gemini 3 Flash81% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/5290API
curl https://kongchang.com/api/v1/knowledge/claims/5290MCP
get_claim(id=5290)