Claude Sonnet 4
- Framework: Responsible Scaling Policy (RSP)
- 2 statements about capability levels
- 1 test by the provider
- 1 source document
What the provider states
- Chemical, biological, radiological and nuclear · ASL-3 · Not determined
specifically, we focused on ruling out asl-4 for both models, as well as ruling out asl-3 for claude sonnet 4.
Anthropic · 4 May 2025 · Read the source - Chemical, biological, radiological and nuclear · ASL-4 · Not determined
specifically, we focused on ruling out asl-4 for both models, as well as ruling out asl-3 for claude sonnet 4.
Anthropic · 4 May 2025 · Read the source
The provider's own tests
- internal AI research evaluation suite 2 · The provider · Autonomy & replication
however, it performed below threshold on other critical evaluations, including the internal ai research evaluation suite 2, where it underperformed claude sonnet 3.7 (0.365 vs 0.440).
Anthropic · 4 May 2025 · Read the source
No document we read states: a release date, an independent or government test, a safeguard. No incident on record names this version.
Some documents we hold are stored in lower case only, so their quotes are shown in lower case. The source link opens the original.
Previous version: Claude Sonnet 3.7 · Compare the two
Documents listed for this version
- Claude Sonnet 4 and Opus 4 · Anthropic · 4 May 2025