# Reflection AI — Open model safety: lessons from training and evaluating Beam

- Company: Reflection AI (reflection.ai)
- Announced: 2026-11-05
- Category: safety-policy-update
- Coverage: not counted
- Announcement: no
- Group: routine
- Source: https://reflection.ai/blog/open-model-safety-lessons
- Record: https://forck.live/items/32191-open-model-safety-lessons-from-training-and-evaluating-beam
- Subject: Reflection Beam
- Open weights: yes
- Models affected: Beam

Reflection is publishing the safety training methods and evaluation results behind Beam, its first open-weight model, through a research initiative it calls Project Iris. The company says Beam sits on the observed Pareto frontier, declining harmful requests more than all other Western and Chinese open-weight models it tested while still complying with harmless ones. Reflection evaluated Beam with Iris Safety Evaluations, a benchmark covering chemical, biological, radiological and nuclear weapons, cyber offense, self-harm, violence, fraud and privacy, and shares it so others can find gaps in their own models. Because safeguards on open-weight models can be modified or removed after release, a separate Open Safety Framework assesses whether a model's underlying capabilities could raise risk beyond what comparable public models already enable. Beam was trained with pretraining data filtering and a dedicated safety-alignment teacher, combined with a capability teacher through multi-teacher on-policy distillation. Reflection reports that scaling the safety teacher from 100B to 501B parameters with the recipe fixed cut over-refusal by 48.7% relative, alongside a 3.1% decrease in the harmful-request pass rate.

## Evidence

Verbatim from https://reflection.ai/blog/open-model-safety-lessons:

> Beam optimizes the safety-utility tradeoff at the frontier. The model achieves high rates of refusal on dangerous requests while maintaining compliance on legitimate ones, demonstrating that open models can simultaneously maximize both safety and helpfulness without sacrificing either.
> 
> Through Project Iris, Reflection is releasing open-source safety research, evaluation artifacts (e.g. Iris Safety Evaluations), and tools that researchers, developers, policymakers, and enterprises can freely use and build upon, widening access to safety best practices and knowledge.
> 
> Building safe open models requires a thoughtful approach to data, a deep understanding of how to evaluate potential harms, and the tools to mitigate them. For Beam , Reflection’s first open-weight model, we prioritized safety training to reduce harmful assistance while preserving useful responses to legitimate requests, including responses involving sensitive subjects.
> 
> Project Iris is our initiative to build an ecosystem around safety research, benchmarks, and mitigations openly – giving researchers, developers, and policymakers practical ways to assess model safety and examine the standards behind it.

---

Record: https://forck.live/items/32191-open-model-safety-lessons-from-training-and-evaluating-beam
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md