Anthropic Says Unreleased Model Outperforms Mythos 5.1 in Capability and Alignment
Understand the story
On October 24, 2026, The Decoder reported that Anthropic, drawing on a review of UK AI Safety Institute (AISI) cybersecurity testing, claimed that one of its internal unreleased models outperforms Mythos 5.1 in both capability and alignment. This is currently the only report on the matter, with no follow-up developments or responses from any parties.
AI overview of reporting · Updated 2 days ago
Reporting timeline
Explore different aspects of the story through its reporting.
- The DecoderAnthropic says its unreleased model is both more capable and better aligned than Mythos 5.1
In a retrospective on UK AISI cybersecurity testing, Anthropic said one of its internal unreleased models outperforms Mythos 5.1 in both capability and alignment.
Story heat trend
Current heat4·Comparable peak10（10/24 03:00）·Comparable change over 24 hours -49%
The trend compares the same continuously observed sources, which may cover fewer sources than the current heat score. Hover or select the chart to inspect each hour; use the left and right arrow keys to navigate.