Reflection AI 发布 Beam 1.0：501B 参数开源模型跻身 Agent Arena 第12名
美国 Reflection AI 放了个 501B 的 Apache 2.0 开源模型，Agent Arena 第12，是榜单前25里唯一非中国实验室的开源作品。
Reflection AI 发布 Beam-1.0-501B-A23B，总参数 501B、激活 23B，以 Apache 2.0 许可完全开源。该模型在 Agent Arena 开源权重榜单排第12，Net Improvement 为 -3.67%，是美国开源模型中的最高名次，超过 Hy3、MiMo V2.5 Pro 和 MiniMax M3。在 Code Arena: WebDev 上得 1438 分、开源榜第22，是前25名开源模型中唯一非中国实验室的作品，排在 Kimi K2.5 Thinking 和 GLM-5 之前。其 Net Improvement 误差范围为 ±3.84%，与前方的两个 Qwen3.8 模型在统计上接近。完整权重将于本月内发布。
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 💬 11 🔄 5 ❤️ 49 👀 5151 📊 12 ⚡
