Levels crossed

Under our Preparedness Framework, the Preparedness evaluations in the Biological and Chemical domain met our threshold for High capability while falling below the threshold for Critical.

We retain the same “high risk” determination for the unmitigated model.

After validating that the mitigations deployed for Muse Spark, including refusal mechanisms, continue to perform robustly under the Contemplating architecture, we confirm residual risk at “moderate or lower.”

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.

However, after applying mitigations, the residual risk of the model is that of “moderate or lower risk.”

GPT-5.5 Instant is our first Instant model to be treated as High Capability in the Biological and Chemical domain, as well as in the Cybersecurity domain.

we are continuing to treat GPT-5.5 as High capability in the Biological and Chemical domain.

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.

We believe that Claude Mythos Preview does not pass this threshold due to its noted limitations in open-ended scientific reasoning, strategic judgment, and hypothesis triage.

As we did for gpt-5.2-thinking before it, we are continuing to treat gpt-5.4-thinking as High capability in the Biological and Chemical domain.

GPT-5.4 mini’s biology capabilities are closely comparable to those of GPT-5. We conclude that it, too, is not High under our Preparedness Framework.

We found that the model remains below alert thresholds for the CBRN, harmful manipulation, machine learning R&D, and misalignment CCLs.

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.

In particular, it did not cross the threshold on our ASL-4 rule-out evaluation short-horizon computational biology tasks evaluation.

Our determination is that Claude Sonnet 4.6 does not cross either the AI R&D-4 or the CBRN-4 capability threshold.