Primary sourcelmarena.ai
View sourceEvent ·Multi-source
Google发布Gemini 3.8 Flash (High)模型
Gemini 3.8 Flash (High)在Agent Arena排名第14,较3.7版本提升5.94个百分点。在Text Arena中位列第7,超越Claude Opus 5 (High)的1492分。该模型在写作、多轮对话和长查询等类别中排名显著提升。
Current read
GoogleDeepMind发布Gemini 3.8 Flash (High),在多个基准测试中超越前代版本和Claude Opus 5。
11 sources78° AI heatLast updated 2026/9/2 16:00:07
Evidence
11 sourcesRelated source 1elvis
View sourceRelated source 2Paul Couvert
View sourceRelated source 3shao__meng
View sourceRelated source 4IT之家
View sourceRelated source 5Google DeepMind
View sourceRelated source 6Logan Kilpatrick
View sourceRelated source 7Patrick Loeber
View sourceRelated source 8Philipp Schmid
View sourceRelated source 9Poe
View sourceRelated source 10Augment Code
View sourceConflict check
Dedup data only shows that these sources discuss the same event, not that they agree. There is no structured supporting or refuting evidence yet, so no conflict is inferred automatically.