Reflection's Beam: A 501B open-weight model that matches giants with 3–4× less compute

Beam: Reflection's 501B open-weight model

Reflection's Beam: A 501B open-weight model that matches giants with 3–4× less compute

Reflection released Beam, its first open-weight model: a 501B-parameter sparse Mixture-of-Experts with 23B active parameters, trained on 23.8T tokens and an RL run of over 100 million rollouts on 10.5K NVIDIA GB300 GPUs. Beam targets coding and agentic tasks, trading raw capability for inference efficiency—matching GLM-5.2 on reasoning with 3–4× less compute. Weights and technical report arrive later this month.

Even when training Beam with one-day staleness—107 weight versions behind the current policy—the numerics remain stable.
  1. Ariarule

    Always glad to see more open-weight models, but this caption on the 2nd demo image had me do a double-take: "Land or Water Generalization Experiment: We recreated the viral X puzzle by asking Beam to create a fixed 180×90 grid for longitudes -179° to 179° and latitudes -89° to 89°, with 16,200 points. This puzzle is a few days old, so could not appear in the training data, thus testing the model’s generalization. Beam gets 95.5% coverage right, putting us between Opus 5 (92.5%) and Fable 5 (97.8%), which shows how well it generalizes to novel new tasks."

    Oof, no, this "puzzle is a few days old" is incorrect even if it's a social media trend just recently. Asking a model to generate a world map in this way is _at least_ from August 2025 as it appeared on LessWrong at that time: https://www.lesswrong.com/posts/xwdRzJxyqFqgXTWbH/how-does-a...

  2. htrp

    > Beam is a sparse Mixture-of-Experts model with 501 billion total parameters, 23 billion active, built for coding, reasoning, and agentic workloads.

    > Beam’s capabilities come from major investments in both pretraining and reinforcement learning (RL). We pretrained the model on 23.8 trillion diverse, curated, high-quality tokens from the web and proprietary licensed datasets, matching or outperforming available similar-sized open base models. In parallel, we developed the algorithms, training environments, and infrastructure needed to sustain high-compute RL at exceptional scale. Our high-compute RL run generated over 100 million rollouts on 10.5K NVIDIA GB300 GPUs over 4 weeks of training.

    Early access, no weights no tech details, just a sign up here for info

  3. algoth1

    Does this one also routes to Claude under the hood like Reflection 70B did? I recall they even run a basic regex to remove "Claude" from the output. Then they promised to be completely transparent on the postmortem (they claim they had no idea what had happened), but the postmortem never came

  4. wren6991

    I thought it would be interesting to look at some key figures vs another contemporary model in the same weight class (DeepSeek V4.1 Flash)

    DS V4.1F Beam

    LM total params 552B 501B

    LM active params (prefill) 8B 23B

    LM active params (decode) 16B 23B

    N-gram/PLE params 196B 0

    Pretrain tokens 45T 28T

    Disk KV bytes/token (FP4) 890 No information

    Vision Yes (pretrain) No

    Weights available Yes (launch day) "This month"

    Weights licence MIT Apache 2.0

    At first blush the benchmarks are impressive, but to paraphrase Linus: "Talk is cheap, show me the weights." :-)

  5. NorwegianDude

    Bigger and still worse than existing free Chinese models that are smaller? Open weight models are nice, but at this point it seems western models are very far behind Chinese ones, despite Chinese companies publishing a lot of their findings. I hope we get more open models and more providers, as being stuck with a model from China or US with no competition is risky.

    Google does do a great job with Gemma models. It's one of the few language models actually good at language. OpenAI's top closed models can't even write norwegian correctly.

  6. efficient_dairy

    I don't find open-weight models that impressive anymore. MiMo-V2.6 already showed that you can have a not so crazy architecture and enough compute, the bottleneck is then just the data. OAI and Anthropic are largely the frontier models because of the synthetic data they made. They have a large customer base and have the user's data as well as knowing what tasks their customers use the models for and what domain they should get synthetic data for.

  7. onlyrealcuzzo

    This appears to be larger than DeepSeek v4.1 Flash, more expensive to run, and worse on every measured metric.

    Am I missing something?

  8. reissbaker

    Instead of yet another mediocre but fully-made-in-the-West open model (alongside Mistral, Trinity, Poolside, Inkling, etc etc) I'd really love for a Western neloab start the same way Qwen did: by focusing on post-training. Qwen's first release was a Llama 1 finetune [1]! Once they made it useful, they started working their way back in the stack to also do their own pretraining, etc. Starting with pretraining feels like such a waste: there's millions of dollars of crystallized compute and data sitting around in the Chinese model weights. Why not start with one of those, and only work your way back to pretraining once you've released something you can prove is useful?

    1: https://en.wikipedia.org/wiki/Qwen

More from this day

2026-10-05