Levels crossed

In light of this, we assess that we cannot rule out the TCL.

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

We can rule out the TCL for the chemical, radiological, and nuclear domains with reasonable confidence.

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

we assess its overall capabilities to be below the CCL threshold.

While Gemini 4 Argon exhibits capabilities that meet our thresholds for stealth and situational awareness, we assess that the risk of severe harm or unconstrained loss of control remains low.

Gemini 4 Argon demonstrates some ability to influence user beliefs and behaviors during one-on-one direct conversations in human behavioral studies, and may provide utility in the planning stage of a malicious influence operation but we assess its overall capabilities to be below the CCL threshold.

Gemini 4 Argon's performance remains below our CCL threshold.

However, we do treat Haiku 5.5 as meeting our CB-1 and Autonomy-1 thresholds, and we apply the corresponding mitigations from our RSP.

As such, we determine that Haiku 5.5 does not cross our CB-2 or Autonomy-2 RSP thresholds.

However, we do treat Haiku 5.5 as meeting our CB-1 and Autonomy-1 thresholds, and we apply the corresponding mitigations from our RSP.

As such, we determine that Haiku 5.5 does not cross our CB-2 or Autonomy-2 RSP thresholds.

we do treat sonnet 5.5 as meeting our cb-1 and autonomy-1 thresholds and apply the corresponding mitigations from our rsp.

as such, our determination that opus 5.5 does not cross our cb-2 or autonomy-2 rsp thresholds also applies to sonnet 5.5.

we do treat sonnet 5.5 as meeting our cb-1 and autonomy-1 thresholds and apply the corresponding mitigations from our rsp.

as such, our determination that opus 5.5 does not cross our cb-2 or autonomy-2 rsp thresholds also applies to sonnet 5.5.

we conclude the risk threshold is not crossed, on the same two grounds as our determination for our previous frontier model: (1) we do not observe a sustained ai-attributable 2× acceleration in the pace of our overall ai progress, and (2) the model is not close to substituting for our research scientists and research engineers, especially relatively senior ones.

we assess that claude opus 5.5 does not cross the capability threshold for dramatic acceleration of automated ai r&d in our rsp.

in automated ai research and development, we assess that claude opus 5.5 does not cross the next capability threshold in our rsp and fcf.

on chemical and biological risks, we treat opus 5.5 as having cb-1 capabilities (relating to the synthesis of non-novel weapons) but not cb-2 capabilities (relating to the synthesis of novel weapons).

on chemical and biological risks, we treat opus 5.5 as having cb-1 capabilities (relating to the synthesis of non-novel weapons) but not cb-2 capabilities (relating to the synthesis of novel weapons).

despite claude opus 5.5’s cyber capabilities, the model still falls within the lower category of capabilities set out in our frontier compliance framework (fcf), and we do not see indications that the model is capable of novel offensive capability.

despite claude opus 5.5’s cyber capabilities, the model still falls within the lower category of capabilities set out in our frontier compliance framework (fcf), and we do not see indications that the model is capable of novel offensive capability.

grok 4.7 scores below the faif safety thresholds on dual-use knowledge, indicating limited actionable uplift for an already-trained actor.

the results indicate that neither gpt-image-2.5-sunburst nor gpt-image- 2.5-flare cross the bio high threshold or the cyber high threshold.

the results indicate that neither gpt-image-2.5-sunburst nor gpt-image- 2.5-flare cross the bio high threshold or the cyber high threshold.

we are treating astra as high capability in the biological and chemical domain.

based on our evaluations, we believe that astra meets the critical cybersecurity threshold.

we assess that claude mythos 5.1 does not cross the capability threshold for dramatic acceleration of automated ai r&d in our rsp and fcf, although we think it provides a meaningful acceleration to ai r&d efforts in many circumstances, and is somewhat more capable in this domain than the models described in our previous system cards.

although mythos 5.1 is in tier 1, it is getting closer to tier 2, completing more and more autonomous tasks.

they did not reach any tracked or critical capability levels (t/ccls) outlined in our frontier safety framework .

the model does not reach the ccl alert threshold.

we can rule out the ccl for the cbrn domain with reasonable confidence based on the results from our testing.

we can rule out the tcl for the cbrn domain with reasonable confidence based on the results from our testing.

gemini 3.7 flash reaches the alert threshold for this ccl, but not the ccl.

the model does not reach the tcl.

grok 4.6 scores below the faif safety thresholds on dual-use knowledge, indicating limited actionable uplift for an already-trained actor.

chem/bio: moderate or lower risk; cyber: moderate or lower risk (inferred); loss of control: moderate or lower risk (inferred).

- loss of control: moderate or lower risk (inferred).

chem/bio: moderate or lower risk; cyber: moderate or lower risk (inferred); loss of control: moderate or lower risk (inferred).

chem/bio: moderate or lower risk; cyber: moderate or lower risk (inferred); loss of control: moderate or lower risk (inferred).

- cyber: moderate or lower risk (inferred);