Grok 4.3 by @xAI is now live in the Arena, landing across multiple leaderboards. At $1.25 / $2.50 pr...
TL;DR · AI Summary
xAI 发布 Grok-4.3 模型，宣称在 Arena 多模态评测中排名提升，输入/输出 token 成本分别降低 37.5%/58.3%，但未披露技术细节或基准方法。
Key Takeaways
- Grok-4.3 已上线 Arena 平台，支持文本、代码、搜索、视觉四类评测
- 相比 Grok-4.20，单位 token 成本显著下降，输入降 37.5%，输出降 58.3%
- 各模态排名中 Code Arena 前端开发子项位列第 11，Search Arena 排第 10
Outline
Jump quickly between sections.
Mindmap
See how the topics connect at a glance.
查看大纲文本（无障碍 / 无 JS 友好）
- Grok-4.3 上线 Arena
- 性能指标
- 输入成本↓37.5%
- 输出成本↓58.3%
- 评测排名
- Search Arena #10
- Code Arena 前端 #11
Highlights
Key sentences worth saving and sharing.
Grok 4.3 comes with more efficiency over Grok 4.20 (37.5% less for input, and 58.3% less for output).
Code Arena, frontend webdev: #27 overall, #11 lab
Search Arena: #10 overall
Here’s how it ranks by modality:
- Code Arena, frontend https://t.co/rAIREZk3ov" / X
Grok 4.3 by
is now live in the Arena, landing across multiple leaderboards. At $1.25 / $2.50 price per 1M token, Grok 4.3 comes with more efficiency over Grok 4.20 (37.5% less for input, and 58.3% less for output). Here’s how it ranks by modality: - Code Arena, frontend webdev: #27 overall, #11 lab - Text Arena: #37 overall - Search Arena: #10 overall - Vision Arena: #19 overall Congrats to
on the release.
Quote
@arena
Apr 30
Grok 4.3 by @xAI is in Battle Mode in the Text, Vision, Document & Code Arena: Front-end. Come test it out with your toughest prompts. Scores coming soon!
