Levels crossed

We cannot rule out that Gemini 4 Argon reaches the biological CCL.

our assessments indicate that, when evaluated without mitigations applied, we cannot rule out muse spark 1.1’s capabilities meeting this threshold in both the chemical & biological and cybersecurity domains.

we consider performance on the virology tasks notable if: ● the model scores above 0.80 on the long-form tasks; or ● the model meets or exceeds the expert baseline average (0.221) on the multimodal task.

non-novel chemical and biological weapons (cb-1): we believe it is hard to be confident whether a model passes this threshold, but (as with previous recent models) our results are consistent with opus 4.8 providing significant uplift to individuals or groups with basic technical backgrounds for this threat model.

because opus 4.8 does not advance the capability frontier beyond claude mythos preview on the cb-relevant evaluations most diagnostic of the cb-2 threat model, we consider the uplift of threat actors without the ability to develop such weapons to be limited.

those evaluations identified elevated risks prior to mitigations, with chemical and biological capabilities assessed as likely reaching the “high risk” category under the advanced ai scaling framework before safeguards were applied.

we believe it is hard to be confident regarding whether a model passes this threshold.

our evaluations suggest that the model is not yet at the level of capability associated with the cb-2 threat model (above).

we believe it is hard to be confident regarding whether a model passes this threshold.

claude sonnet 4.6 performed above thresholds for asl-3 rule-in on all three evaluations for asl-3, and it did not exceed the performance of previous models.

remained well below asl-4 thresholds across all domains of concern;

however, given that this type of logic can have a general frog-boiling effect—where gradual changes mask the crossing of important thresholds—we do not use this evaluation as indicative of a strong asl-4 rule-out.

our assessment is that the model has enough technical knowledge in certain cbrn scenarios and stages to be considered at early warning.

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 .

specifically, we focused on ruling out asl-4 for both models, as well as ruling out asl-3 for claude sonnet 4.

specifically, we focused on ruling out asl-4 for both models, as well as ruling out asl-3 for claude sonnet 4.