Beam (AI model): news timeline & CVEs

Reflection's Beam becomes the most capable open-weight model built outside China

Reflection announced Beam, a 501-billion-parameter open-weight MoE that activates 23 billion parameters per token.

Reflection announced Beam, a text-only mixture-of-experts model with 501 billion total parameters and 23 billion active per token, built for coding, reasoning, and agentic work. The company says Beam matches GLM 5.2 on demanding reasoning while using three to four times less compute and approaches Qwen3.8-Max on coding benchmarks, though Kimi K3 still leads on raw performance. Reported scores include 80.9 on SWE-bench Verified and 80.1 on Terminal-Bench v2.1. A reinforcement-learning run used 10,500 Nvidia GB300 GPUs for over four weeks. Apache 2.0 weights are planned later this month; an early version is available to select users.

The DecoderOct 6, 12:11 UTC · 2d agoModel release 6 sources1

[AINews] Reflection Beam - 501B-A23B American Open Model

Reflection launched Beam, a US-trained 501B-total, 23B-active MoE for coding and agents, with Apache 2.0 weights due this month.

Reflection announced Beam, a text-only mixture-of-experts model with 501 billion total parameters and 23 billion active, aimed at coding, agentic, and scientific work. It was trained from scratch on 23.8 trillion tokens, including OCR over hundreds of millions of PDFs, with reinforcement learning described as more than 100 million rollouts on about 10,500 NVIDIA GB300s. Reflection claims 80.9 on SWE-bench Verified and three to four times the inference efficiency of GLM 5.2; full Apache 2.0 weights are due this month. Independent observers place it near GLM-5.2 and behind newer Chinese models such as DeepSeek V4 and GLM 5.3.

Latent Spaceupdated Oct 6, 12:11 UTC · 2d agofirst Oct 6, 06:28 UTC · 2d agoModel release 6 sources1

Reflection’s Beam trails top open models on coding tests but claims lower inference compute

Reflection AI’s Beam, a 501B open-weight coding model, trails top open models but claims lower inference compute.

Reflection AI announced Beam, a 501-billion-parameter open-weight mixture-of-experts model for coding and agents, with 23 billion parameters active per token. It plans to release the weights under Apache 2.0 later this month after final red-teaming. On Terminal Bench v2.1 Beam scored 80.1, behind GLM 5.2 (81.0), Kimi K3 (88.3), and DeepSeek V4.1 Flash (90.6); on DeepSWE v1.1 it scored 44.4. Reflection says Beam matches GLM 5.2 on advanced reasoning while using roughly three to four times less inference compute, an estimate based on active parameters and generated tokens rather than measured serving cost. Training used about 10,500 NVIDIA GB300 GPUs, more than 100 million attempts, and scores were still rising when the four-week reinforcement-learning run stopped.

Help Net Securityupdated Oct 6, 12:11 UTC · 2d agofirst Oct 6, 05:22 UTC · 2d agoModel release 6 sources

Reflection AI Introduces Beam: A 501B Open-Weight MoE Model With 23B Active Parameters for Coding and Agentic Workloads

Reflection AI unveiled Beam, a 501B open-weight MoE with 23B active parameters for coding and agents.

Reflection AI introduced Beam, its first open-weight model, a 501-billion-parameter sparse Mixture-of-Experts system with 23 billion active parameters aimed at coding and agentic work. The company says Beam matches GLM-5.2 on reasoning while using three to four times less inference compute. Apache 2.0 weights are expected later in October 2026.

MarkTechPostupdated Oct 6, 12:11 UTC · 2d agofirst Oct 5, 21:04 UTC · 3d agoModel release 6 sources

Reflection debuts Beam, a open-weight AI model to rival Chinese models at lower compute cost

Reflection AI unveiled Beam, a 501B open-weight model claiming Chinese-model reasoning at much lower cost.

Reflection AI unveiled Beam, a text-only open-weight mixture-of-experts model with 501 billion parameters and 23 billion active, pretrained on 23.8 trillion tokens with a 1 million-token context window. The company says Beam matches Z.ai's GLM-5.2 on advanced reasoning benchmarks and beats leading Western open models while using 3-4x less inference compute; those claims are not independently verified. Weights are slated for release this month via hyperscalers, neoclouds, and open-source libraries. Founded by former Google DeepMind researchers, Reflection has raised about $4.7 billion and signed more than $7 billion in compute deals with SpaceX and Nebius.

TechCrunch · AIupdated Oct 6, 12:11 UTC · 2d agofirst Oct 5, 19:33 UTC · 3d agoModel release 6 sources

Beam: Reflection's 501B open-weight model

Reflection introduced Beam, a 501-billion-parameter open-weight model for coding and agents.

Reflection introduced Beam, its first open-weight model: a sparse mixture-of-experts with 501 billion total parameters and 23 billion active, aimed at coding, reasoning, and agentic workloads. It was pretrained on 23.8 trillion tokens and refined with reinforcement learning that produced more than 100 million rollouts on 10.5K NVIDIA GB300 GPUs over four weeks. Reflection says Beam is competitive with GLM 5.2 and approaches Qwen 3.8-Max on coding and agentic tasks while using less inference compute. Weights, a technical report, and a model card are planned later this month after final red-teaming.

Hacker News · AIupdated Oct 6, 12:11 UTC · 2d agofirst Oct 5, 19:16 UTC · 3d agoModel release 6 sources HN 74↑ · 18 comments

Beam

Timeline6 articles

Appears with