# Reflection AI's Beam declines 89% of harmful requests in safety tests

> Original title: Beam achieves the highest refusal/pivot rate among the Western and Chinese open-weight models tested, declining 89% of harmful requests w...

- Source: Reflection
- Published: 2026-11-05T17:01:43.000Z
- Bad Influence: https://badinfluence.news/items/q7inuh0q93ootqjdq0x3smwmr
- Original: https://x.com/reflection_ai/status/2118388300314538457

## Summary

Reflection AI reports that Beam declines 89% of harmful requests and responds to 82% of safety-related harmless requests. The company says this is the highest refusal rate among the Western and Chinese open-weight models it tested.

## Post

Beam achieves the highest refusal/pivot rate among the Western and Chinese open-weight models tested, declining 89% of harmful requests while successfully responding to 82% of safety-related harmless requests—demonstrating that open models can achieve strong safety and helpfulness without compromise.

![](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Fmedia%2FHWYG7qlXMAAbr7u.jpg&mode=thumb&exp=1794096000&sig=9a03983b7e1e777b)