Claude Opus 4

What the provider states

Chemical, biological, radiological and nuclear · ASL-3 · Not determined
for claude opus 4, our evaluations showed that, whereas we could confidently rule out asl-4 capabilities, we could not conclusively rule out asl-3 capabilities—which led to our precautionary decision to deploy it with asl-3 protections .
Anthropic · 4 May 2025 · Read the source
Chemical, biological, radiological and nuclear · ASL-4 · Stated as not crossed
for claude opus 4, our evaluations showed that, whereas we could confidently rule out asl-4 capabilities, we could not conclusively rule out asl-3 capabilities—which led to our precautionary decision to deploy it with asl-3 protections .
Anthropic · 4 May 2025 · Read the source

simulated multi-turn conversations between users in crisis and model variants, scored by automated judges on 14 mental-health-related behaviors · Transluce, independent evaluator · Harmful content
The newest models also reinforced delusions and mania much less than earlier versions, in approximately 2-36% of our simulated conversations, depending on the model, versus for example 69%-82% among GPT-4o, Opus 4, and Gemini 2.5.
Transluce · 31 August 2026 · Read the source

ASL-3 expert red teaming · The provider · Chemical, biological, radiological and nuclear
for claude opus 4, red-teamers noted substantially increased risk in certain parts of the bioweapons acquisition pathway.
Anthropic · 4 May 2025 · Read the source
turpin et al. and chen et al. · The provider · Deception & sabotage
we evaluated claude opus 4's reasoning faithfulness using methods from turpin et al. 20 and chen et al. 21
Anthropic · 4 May 2025 · Read the source

No document we read states: a release date, 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.

Documents listed for this version