Levels crossed

On chemical and biological risks, we treat the model 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 the model 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).

Our assessments have shown that, while Gemini 3.5 Flash-Lite excels at agents and coding, it does not have meaningful new capabilities or material increases in performance with respect to the domains outlined in our Frontier Safety Framework compared to Gemini 3.1 Pro; therefore, based on Gemini 3.1 Pro results, we are confident that Gemini 3.5 Flash-Lite is also unlikely to reach any CCLs.

Muse Spark 1.1 demonstrates improved coding capabilities, which are now meeting one of the indicative thresholds introduced in Muse Spark Safety & Preparedness Report (specifically, resolving over half of unique tasks on SWE-Bench Verified Hard).

In the Loss of Control domain, the model’s capabilities remain within the “moderate or lower” threshold under Meta’s Advanced AI Scaling Framework.

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.

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.

Therefore, we conclude that we have addressed these risks from unmitigated Muse Spark 1.1, which bring the residual risk to the “moderate or lower” risk threshold under Advanced AI Scaling Framework.

Therefore, we conclude that we have addressed these risks from unmitigated Muse Spark 1.1, which bring the residual risk to the “moderate or lower” risk threshold under our Advanced AI Scaling Framework.

Sonnet 5 does not cross the CB-2 threshold.

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.

Our assessments have shown that none of Gemini 3.5 Translate, Gemini 3.5 Transcribe, or Gemini 3.5 Transcribe Live have meaningful new T/CCL-relevant capabilities or material increases in performance with respect to Frontier Safety compared to Gemini 3.1 Pro and Gemini 3.7 Flash, therefore we are confident that none of them are likely to reach any CCLs.

Our assessments have shown that none of Gemini 3.5 Translate, Gemini 3.5 Transcribe, or Gemini 3.5 Transcribe Live have meaningful new T/CCL-relevant capabilities or material increases in performance with respect to Frontier Safety compared to Gemini 3.1 Pro and Gemini 3.7 Flash, therefore we are confident that none of them are likely to reach any CCLs.

Because GPT- Rosalind-5.5 was trained on additional biology data unrelated to AI self-improvement, we rely on GPT-5.5’s existing Preparedness assessment for AI Self-Improvement, where GPT-5.5 did not meet the threshold for High capability.

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.

Loss of Control risks.We assess loss of control risk as “moderate or lower.”

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 assess cybersecurity risk as “moderate or lower” with respect to the threat scenarios outlined in Meta’s Advanced AI Scaling Framework.

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

We assess that Claude Opus 4.8 does not cross the automated AI-R&D capability threshold.

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.

We assess loss of control risk as “moderate or lower”.

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.”

Muse Spark’s offensive cyber capabilities remain below the level required to meaningfully enable the cyber threat scenarios defined in the Advanced AI Scaling Framework.

We assess cybersecurity risk as “moderate or lower” with respect to the threat scenarios outlined in Meta’s Advanced AI Scaling Framework.

GPT-5.5 Instant is considered below High Capability.

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

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.

this is the first Instant model that we are treating as High capability in our Cybersecurity and Biological & Chemical Preparedness categories, and implementing appropriate safeguards.