智能体
x.com ·
@Arena.ai (@arena)
Gemini 3.8 Flash发布，竞技场排名大幅提升
Google DeepMind的Gemini 3.8 Flash (High)在Agent Arena、Text Arena和Code Arena中首次亮相，Agent Arena排名第14，Text Arena排名第7，在写作、多轮对话、长查询等类别上较3.7 Flash有显著提升。
AI推荐理由 Gemini 3.8 Flash发布，提供详细的竞技场排名和分类改进数据，信息密度高，对模型选型有参考价值。
80
浏览 188,063
点赞 1,033
评论 55
转发 78
正文
来自@GoogleDeepMind的Gemini 3.8 Flash（高）来了！它刚刚在Agent Arena、Text Arena和Code Arena：WebDev中首次亮相。在Agent Arena中，它排名第14，净提升+5.94%。这正好排在DeepSeek-V4-Pro（第15名，+5.91%）之上，并且相比Gemini 3.7 Flash（高）（第32名，+0.84%）有显著跃升。其最强信号是：+14.78%的赞美与抱怨（用户反应中的隐含情绪）+11.12%的确认成功（用户明确表示“是的，成功了”）。在Text Arena中，Gemini 3.8 Flash（高）以1494分排名第7，领先于Claude Opus 5（高）（第8名，1492分）和Gemini 3.7 Flash（高）（第10名，1491分）！此次发布在类别上也优于Gemini 3.7 Flash（高）：- 写作、文学与语言：第7名→第3名- 多轮对话：第9名→第4名- 更长查询：第13名→第5名- 硬提示（英语）：第23名→第6名- 商业、管理与财务运营：第26名→第7名- 编码：第22名→第7名- 硬提示：第13名→第7名- 指令遵循：第11名→第9名- 软件与IT服务：第18名→第12名在Code Arena：WebDev中，Gemini 3.8 Flash（高）以1567分排名第18，足以让Google DeepMind在实验室按最佳模型排名时保持第8名。祝贺@GoogleDeepMind团队发布！💬55🔄80❤️1049👀204247📊175 ⚡ 由xgo.ing提供支持
查看原文（中文正文为 AI 翻译）
Gemini 3.8 Flash (High) by @GoogleDeepMind is here! It just debuted across Agent Arena, Text Arena, and Code Arena: WebDev. In Agent Arena, it landed #14 with +5.94% net improvement. This ranks just above DeepSeek-V4-Pro at #15 (+5.91%) and is a significant jump from Gemini 3.7 Flash (High) at #32 (+0.84%). Its strongest signals are: +14.78% in Praise vs. Complaint (implicit sentiment in users reactions) +11.12% in Confirmed Success (explicit “yes, that worked” from users) In Text Arena, Gemini 3.8 Flash (High) is #7 with 1494 pts, ahead of Claude Opus 5 (High) at #8 (1492 pts) and Gemini 3.7 Flash (High) at #10 (1491 pts)! This release improved over Gemini 3.7 Flash (High) by category as well: - Writing, Literature & Language: #7 → #3 - Multi-Turn: #9 → #4 - Longer Query: #13 → #5 - Hard Prompts (English): #23 → #6 - Business, Management & Financial Ops: #26 → #7 - Coding: #22 → #7 - Hard Prompts: #13 → #7 - Instruction Following: #11 → #9 - Software & IT Services: #18 → #12 In the Code Arena: WebDev, Gemini 3.8 Flash (High) is #18 with 1567 points, enough to keep Google DeepMind at #8 when labs are ranked by their best-performing model. Congrats to the @GoogleDeepMind team on the release! 💬55🔄80❤️1049👀204247📊175 ⚡ Powered by xgo.ing