Levels crossed

For AI self-improvement, evaluations of final checkpoints indicate that, like its predecessor models, GPT-5.5 does not have a plausible chance of reaching a High threshold.

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

We therefore treat VulnLMP as important evidence that GPT-5.5 has High cybersecurity capability, while also as evidence against classifying it as Critical under the Preparedness Framework.

we are treating GPT-5.5 as High capability in the Cybersecurity domain, but below Critical.

that Opus 4.7 does not cross the threshold for automated AI R&D;

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).

Our assessments have shown that Gemini 3.1 Flash Audio is less capable than Gemini 3.1 Pro.

The main reason we have determined that Claude Mythos Preview does not cross the threshold in question is that we have been using it extensively in the course of our day-to-day work and exploring where it can automate such work, and it does not seem close to being able to substitute for Research Scientists and Research Engineers—especially relatively senior ones.

We assess that Claude Mythos Preview does not cross the automated AI-R&D capability threshold.

we have concluded that Claude Mythos Preview does not cross the RSP automated AI R&D threshold of compressing two years of progress into one.

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.

For AI self-improvement, evaluations of final checkpoints indicate that, like its predecessor models, gpt-5.4-thinking does not have a plausible chance of reaching a High threshold.

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.

As we did for gpt-5.3-codex, we are treating gpt-5.4-thinking as High capability in the Cybersecurity domain, and applied safeguards as described in the Safeguard section below.

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.

Our assessments have shown that Gemini 3.1 Flash-Lite is less capable than Gemini 3.1 Pro, therefore based on Gemini 3.1 Pro, we are confident that Gemini 3.1 Flash-Lite is also unlikely to reach any CCLs.

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

As previous models passed the alert threshold for cyber, we performed more additional testing in this domain on Gemini 3.1 Pro with and without Deep Think mode, and found that the model remains below the cyber CCL.

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

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.

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

For AI R&D capabilities, we found that Claude Opus 4.6 has saturated most of our automated evaluations, meaning they no longer provide useful evidence for ruling out ASL-4 level autonomy.

The model crossed or met thresholds on all ASL-3 evaluations except our synthesis screening evasion, consistent with incremental capability improvements driven primarily by better agentic workflows.

Claude Opus 4.6 is our strongest biology model to date and demonstrates meaningful capability improvements, but we do not believe it merits ASL-4 safeguards.

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

It does not reach High capability on AI self-improvement.

We are also treating GPT-5.3-Codex as High risk in the Biological and Chemical domain, and applying the same safeguards as for our other deployments of models that reach this designation.

This is the first launch we are treating as High capability in the Cybersecurity domain under our Preparedness Framework, activating the associated safeguards.

Our determination is that Claude Opus 4.5 does not cross either the AI R&D-4 or CBRN-4 capability threshold.

We determine that Claude Opus 4.5 does not cross the CBRN-4 threshold.