← 返回归档

帖子详情

查看 X 原文
L
lmarena.ai@lmarena_ai
Exciting news: Beam-1.0-501B-A23B by @Reflection_AI just landed #12 among open weight models in Agent Arena with -3.67% Net Improvement, and #22 among open in Code Arena: WebDev with 1438 pts. It’s also fully open under Apache 2.0. On the Agent Arena leaderboard, Beam 1.0 is the top-ranked US model among open models, landing at #12 . That puts it ahead of Hy3, MiMo V2.5 Pro and MiniMax M3. Its margin of error is wide (±3.84% on Net Improvement), so it’s statistically closer to the two Qwen3.8 models just above it than its rank suggests. On Code Arena: WebDev, 24 of the top 25 open models come from Chinese labs. The one exception is Reflection’s Beam 1.0 (Apache 2.0). It ranks #22 among open models, which makes it the top US open model on the board, just ahead of Kimi K2.5 Thinking and GLM-5. Congrats to the @Reflection_AI team on this solid open weights release! Reflection @reflection_ai Introducing Beam: a highly efficient agentic open model with 501B total parameters and 23B active. - Frontier reasoning efficiency - Advances the Western open frontier on coding & agentic tasks - Trained end-to-end from scratch Full weights release this month. Learn more about Beam: reflection.ai/beam 🔗 View Quoted Tweet
媒体保存失败：[Errno 104] Connection reset by peer
媒体保存失败：[Errno 104] Connection reset by peer
媒体保存失败：[Errno 104] Connection reset by peer
帖子 ID
2111084024336884097
Markdown
/app/data/archive/2026/10/16/lmarena_ai/2111084024336884097/post.md
保存状态
complete
查看 Markdown 内容
---
tweet_id: "2111084024336884097"
author: "lmarena_ai"
published_at: "2026-10-16T13:17:08+00:00"
source_url: "https://x.com/arena/status/2111084024336884097"
---

Exciting news: Beam-1.0-501B-A23B by [@Reflection\_AI](https://x.com/Reflection_AI) just landed #12 among open weight models in Agent Arena with -3.67% Net Improvement, and #22 among open in Code Arena: WebDev with 1438 pts. It’s also fully open under Apache 2.0.  
  
On the Agent Arena leaderboard, Beam 1.0 is the top-ranked US model among open models, landing at #12. That puts it ahead of Hy3, MiMo V2.5 Pro and MiniMax M3. Its margin of error is wide (±3.84% on Net Improvement), so it’s statistically closer to the two Qwen3.8 models just above it than its rank suggests.  
  
On Code Arena: WebDev, 24 of the top 25 open models come from Chinese labs. The one exception is Reflection’s Beam 1.0 (Apache 2.0). It ranks #22 among open models, which makes it the top US open model on the board, just ahead of Kimi K2.5 Thinking and GLM-5.  
  
Congrats to the [@Reflection\_AI](https://x.com/Reflection_AI) team on this solid open weights release!

![Tweet Image](https://pbs.twimg.com/media/HUwObk3bIAAPoRj.jpg)

![Reflection](https://pbs.twimg.com/profile_images/2107189477575696385/id98cuOX_normal.jpg)

Reflection@reflection\_ai

Introducing Beam: a highly efficient agentic open model with 501B total parameters and 23B active.  
  
- Frontier reasoning efficiency  
- Advances the Western open frontier on coding & agentic tasks  
- Trained end-to-end from scratch  
  
Full weights release this month.  
  
Learn more about Beam: [reflection.ai/beam](http://reflection.ai/beam)

![Tweet Image](https://pbs.twimg.com/media/HT46mRYXwAAxTdt.jpg)

[🔗 View Quoted Tweet](https://x.com/reflection_ai/status/2107186849370247235)