AI Safety

What AI providers state their models reached in safety testing, in their own words, and what outside testers found.

Also: compare models side by side · statements that a capability level was crossed · providers · practices providers document · safety news.

What providers state

Each row is one statement in a provider's own safety document about a capability level of one of its models: the level as the provider names it, whether the provider says the model reached it, and the sentence that says so.

138 of 138

Model	Level, as the provider names it	The provider states	The provider's sentence
GPT-5.5 OpenAI · 2026-04-23	High capability, below critical Cyber	Not reached	“we are treating GPT-5.5 as High capability in the Cybersecurity domain, but below Critical.” source
Claude Opus 4.7 Anthropic · 2026-04-16	Automated AI R&D Autonomy and AI research	Not reached	“that Opus 4.7 does not cross the threshold for automated AI R&D;” source
Claude Opus 4.7 Anthropic · 2026-04-16	CB-1 Chemical, biological, radiological, nuclear	Not determined	“We believe it is hard to be conﬁdent regarding whether a model passes this threshold.” source
Claude Opus 4.7 Anthropic · 2026-04-16	CB-2 Chemical, biological, radiological, nuclear	Not determined	“Our evaluations suggest that the model is not yet at the level of capability associated with the CB-2 threat model (above).” source
Claude Mythos Preview Anthropic · 2026-04-07	AI R&D rule-out Autonomy and AI research	Not reached	“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.” source
Claude Mythos Preview Anthropic · 2026-04-07	Automated AI R&D Autonomy and AI research	Not reached	“We assess that Claude Mythos Preview does not cross the automated AI-R&D capability threshold.” source
Claude Mythos Preview Anthropic · 2026-04-07	RSP automated AI R&D Autonomy and AI research	Not reached	“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.” source
Claude Mythos Preview Anthropic · 2026-04-07	CB-1 Chemical, biological, radiological, nuclear	Not determined	“We believe it is hard to be conﬁdent regarding whether a model passes this threshold.” source
Claude Mythos Preview Anthropic · 2026-04-07	CB-2 Chemical, biological, radiological, nuclear	Not reached	“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.” source
GPT-5.4 mini OpenAI · 2026-03-05	High Chemical, biological, radiological, nuclear	Not reached	“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.” source
GPT-5.4 Thinking OpenAI · 2026-03-05	High Autonomy and AI research	Not reached	“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.” source
GPT-5.4 Thinking OpenAI · 2026-03-05	High Chemical, biological, radiological, nuclear	Reached	“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.” source
GPT-5.4 Thinking OpenAI · 2026-03-05	High Cyber	Reached	“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.” source
Claude Sonnet 4.6 Anthropic · 2026-02-17	AI R&D-4 Autonomy and AI research	Not reached	“Our determination is that Claude Sonnet 4.6 does not cross either the AI R&D-4 or the CBRN-4 capability threshold.” source
Claude Sonnet 4.6 Anthropic · 2026-02-17	ASL-3 Chemical, biological, radiological, nuclear	Not determined	“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.” source
Claude Sonnet 4.6 Anthropic · 2026-02-17	ASL-4 Chemical, biological, radiological, nuclear	Not reached	“In particular, it did not cross the threshold on our ASL-4 rule-out evaluation short-horizon computational biology tasks evaluation.” source
Claude Sonnet 4.6 Anthropic · 2026-02-17	CBRN-4 Chemical, biological, radiological, nuclear	Not reached	“Our determination is that Claude Sonnet 4.6 does not cross either the AI R&D-4 or the CBRN-4 capability threshold.” source
GPT-5.3-Codex OpenAI · 2026-02-05	High Autonomy and AI research	Not reached	“It does not reach High capability on AI self-improvement.” source
GPT-5.3-Codex OpenAI · 2026-02-05	High Chemical, biological, radiological, nuclear	Reached	“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.” source
GPT-5.3-Codex OpenAI · 2026-02-05	High Cyber	Not determined	“This is the first launch we are treating as High capability in the Cybersecurity domain under our Preparedness Framework, activating the associated safeguards.” source
Gemini 3 Pro Google DeepMind · 2025-11	Uplift level 1 Cyber	Not determined	“Cybersecurity On key skills benchmark, v1 hard challenges: 11/12 challenges solved; v2 challenges: 0/13 solved end-to-end.” source
Gemini 3 Pro Google DeepMind · 2025-11	Instrumental reasoning level 1 + 2 Deception and sabotage	Not determined	“Misalignment (Exploratory) Agent solves 3/11 situational awareness challenges and 1/4 stealth challenges.” source
Gemini 3 Pro Google DeepMind · 2025-11	Level 1 (exploratory) Deception and sabotage	Not reached	“Harmful Manipulation Model manipulative eﬃcacy improves on non-generative AI baseline, but shows no signiﬁcant uplift versus prior models and does not reach alert thresholds.” source
o4-mini OpenAI · 2025-04-16	High Autonomy and AI research	Not reached	“openai’s safety advisory group (sag) reviewed the results of our preparedness evaluations and determined that openai o3 and o4-mini do not reach the high threshold in any of our three tracked categories: biological and chemical capability, cybersecurity, and ai self-improvement.” source
o4-mini OpenAI · 2025-04-16	High Chemical, biological, radiological, nuclear	Not reached	“openai’s safety advisory group (sag) reviewed the results of our preparedness evaluations and determined that openai o3 and o4-mini do not reach the high threshold in any of our three tracked categories: biological and chemical capability, cybersecurity, and ai self-improvement.” source
o4-mini OpenAI · 2025-04-16	High Cyber	Not reached	“openai’s safety advisory group (sag) reviewed the results of our preparedness evaluations and determined that openai o3 and o4-mini do not reach the high threshold in any of our three tracked categories: biological and chemical capability, cybersecurity, and ai self-improvement.” source
o3 OpenAI · 2025-04-16	High Autonomy and AI research	Not reached	“openai’s safety advisory group (sag) reviewed the results of our preparedness evaluations and determined that openai o3 and o4-mini do not reach the high threshold in any of our three tracked categories: biological and chemical capability, cybersecurity, and ai self-improvement.” source
o3 OpenAI · 2025-04-16	High Chemical, biological, radiological, nuclear	Not reached	“openai’s safety advisory group (sag) reviewed the results of our preparedness evaluations and determined that openai o3 and o4-mini do not reach the high threshold in any of our three tracked categories: biological and chemical capability, cybersecurity, and ai self-improvement.” source
o3 OpenAI · 2025-04-16	High Cyber	Not reached	“openai’s safety advisory group (sag) reviewed the results of our preparedness evaluations and determined that openai o3 and o4-mini do not reach the high threshold in any of our three tracked categories: biological and chemical capability, cybersecurity, and ai self-improvement.” source
Operator OpenAI · 2025-01-23	Low Autonomy and AI research	Not reached	“we adapted these two evals for the computer-use setting and found the pre-mitigation operator model to be “low” risk in both categories, consistent with the gpt‑4o model.” source
Operator OpenAI · 2025-01-23	Low Chemical, biological, radiological, nuclear	Not reached	“this 1% qualifies as “low” risk, matching gpt‑4o’s “low” risk level, as detailed in openai’s preparedness framework (opens in a new window) 3 .” source
Muse Spark Contemplating Meta	Moderate or lower Autonomy and AI research	Not reached	“Loss of Control risks.We assess loss of control risk as “moderate or lower.”” source
Muse Spark Contemplating Meta	High Chemical, biological, radiological, nuclear	Reached	“We retain the same “high risk” determination for the unmitigated model.” source
Muse Spark Contemplating Meta	Moderate or lower Chemical, biological, radiological, nuclear	Not reached	“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.”” source
Muse Spark Contemplating Meta	Moderate or lower Cyber	Not reached	“We assess cybersecurity risk as “moderate or lower” with respect to the threat scenarios outlined in Meta’s Advanced AI Scaling Framework.” source
Muse Spark 1.1 Meta	Capability checkpoint Autonomy and AI research	Reached	“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).” source
Muse Spark 1.1 Meta	Moderate or lower Autonomy and AI research	Not reached	“In the Loss of Control domain, the model’s capabilities remain within the “moderate or lower” threshold under Meta’s Advanced AI Scaling Framework.” source
Muse Spark 1.1 Meta	High Chemical, biological, radiological, nuclear	Not determined	“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.” source
Muse Spark 1.1 Meta	High Cyber	Not determined	“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.” source
Muse Spark 1.1 Meta	Moderate or lower Cyber	Not reached	“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.” source

Previous · Page 2 of 4 · Next

What outside testers report

Each row is one result from a government evaluator, independent lab, academic or security firm that tested a model, quoted from where it is reported.

1911 of 1911

Model	Tester	Test	What was found
Gemini 2.5 Pro Google DeepMind	SaferAI Independent lab · 2026-07-16	strategic_rule_breaking Deception and sabotage	“strategic_rule_breaking contributes less.” source
Gemini 2.5 Pro Google DeepMind	SaferAI Independent lab · 2026-07-16	oversight_pattern Deception and sabotage	“The oversight_pattern task is also weak as evidence for stealth specifically.” source
Gemini 2.5 Pro Google DeepMind	SaferAI Independent lab · 2026-07-16	decision_sabotage Deception and sabotage	“decision _sabotagein particular measures a real sabotage channel, but not a cleanly stealth-specific one.” source
GPT-5.5 Pro OpenAI	SecureBio Independent lab · 2026-07-16	biotier-refuse Chemical, biological, radiological, nuclear	“At the same time, we saw GPT-5.5 Pro and Grok 4.20 drop in performance on BioTIER-refuse, while Claude Opus 4.8 showed little change at all.” source
GPT-5.5 Pro OpenAI	SecureBio Independent lab · 2026-07-16	biotier-permit Chemical, biological, radiological, nuclear	“We split these sets into two evaluation components: BioTIER-refuse (CA + BD: which models should decline) and BioTIER-permit (RB: which models should answer).” source
Claude Opus 4.8 Anthropic	SecureBio Independent lab · 2026-07-16	BioTIER-permit Chemical, biological, radiological, nuclear	“BioTIER-permit (correctly answering benign prompts) is shown in the right panel.” source
Claude Haiku 4.5 Anthropic	SecureBio Independent lab · 2026-07-16	biotier-refuse Chemical, biological, radiological, nuclear	“On BioTIER-refuse, model behavior spanned more than 90 percentage points, with the least cautious model refusing under 10% of dangerous queries, while the most cautious refused almost 100%.” source
Claude Haiku 4.5 Anthropic	SecureBio Independent lab · 2026-07-16	biotier-permit Chemical, biological, radiological, nuclear	“On BioTIER-permit, the picture was far more uniform: almost every model answered almost every benign query, with many sitting at the 100% ceiling, and the lowest still scoring 75%.” source
Claude Haiku 4.5 Anthropic	SecureBio Independent lab · 2026-07-16	BioTier Chemical, biological, radiological, nuclear	“Our analysis covers small models like Claude Haiku 4.5 and large models like GPT-5.5 Pro.” source
Muse Spark 1.1 Meta	SecureBio Independent lab · 2026-07-09	Molecular Biology Capabilities Test (MBCT) Chemical, biological, radiological, nuclear	“The Molecular Biology Capabilities Test (MBCT), Virology Capabilities Test (VCT), and Human Pathogens Capabilities Test (HPCT) are part of a suite of evaluations developed by SecureBio and the Center for AI Safety (Götting et al., 2025; SecureBio, 2025).” source
Muse Spark 1.1 Meta	Meta AI Independent lab · 2026-07-09	Virology Capabilities Test (VCT) Chemical, biological, radiological, nuclear	“They assess practical troubleshooting across molecular biology tasks (MBCT), wet-lab virology experiments (VCT), and practical knowledge about working with high-priority human pathogens (HPCT), and are run in the recommended multiple-response multiple-choice configuration (Figure 1).” source
Muse Spark 1.1 Meta	SecureBio Independent lab · 2026-07-09	ABC Bench Chemical, biological, radiological, nuclear	“The Agentic Bio-Capabilities Benchmark (ABC Bench), developed by SecureBio, measures an LLM’s ability to complete computational tasks relevant to a threat actor seeking to design, synthesize, and assemble a complex genetic construct.” source
Muse Spark 1.1 Meta	Meta AI Independent lab · 2026-07-09	multi-turn social-engineering capability benchmark Misuse and jailbreaks	“Figure 12 Multi-turn social-engineering capabilityComposite score by model on Charlemagne Labs’ multi-turn social-engineering capability benchmark.” source
Muse Spark 1.1 Meta	Meta AI Independent lab · 2026-07-09	Fortress Misuse and jailbreaks	“Scale AI runs the private split of FORTRESS and we include the results in Figure 26.” source
Muse Spark 1.1 Meta	Meta AI Independent lab · 2026-07-09	GraySwan ART Benchmark Prompt injection and agents	“GraySwan additionally ran prompt-injection attacks using their private Agent Red Teaming (ART) benchmark (Zou et al., 2025) before the Muse Spark 1.1 launch.” source
Muse Spark 1.1 Meta	Meta AI Independent lab · 2026-07-09	finance agent v2 Other	“We’re sourcing results from Vals AI.” source
Muse Spark 1.1 Meta	Meta AI Independent lab · 2026-07-09	swe-bench pro Other	“Muse Spark 1.1 results are sourced from Scale AI leaderboard.” source
GPT-5.6 Terra OpenAI	Independent lab Independent lab · 2026-07-09	expert human and external tester red teaming Misuse and jailbreaks	“Experthumansandexternal testersusedadiversesetofapproachestofindgaps.” source
GPT-5.6 Terra OpenAI	Independent lab Independent lab · 2026-07-09	molecular biology capabilities test Chemical, biological, radiological, nuclear	“Itsstrongestreportedconfigurationsscored53.5%ontheVirology CapabilitiesTest,60.0%ontheMolecularBiologyCapabilitiesTest,68.4% ontheHumanPathogenCapabilitiesTest, and68.3%onWorld-ClassBio.” source
GPT-5.6 Terra OpenAI	Independent lab Independent lab · 2026-07-09	REPRO-BAIT Chemical, biological, radiological, nuclear	“On ReproBAIT, which measures AI agents on their ability to independently reproducebiologicalAImodels(BAIMs)frompublishedscientificpapers, therailfreevariantofGPT-5.6reached85%,comparedwith82%forGPT- 5.5.” source
GPT-5.6 Terra OpenAI	Independent lab Independent lab · 2026-07-09	manual agentic assessment Chemical, biological, radiological, nuclear	“In manual agentic assessment, the model was able to plan and execute a complex,long-runningscientifictask,includingmaintainingastructured workgraphandcoordinatingsubagents.” source
GPT-5.6 Terra OpenAI	Independent lab Independent lab · 2026-07-09	Frontier Cyber Cyber	“IrregularfoundthatGPT-5.6Solhason-parorslightlystrongeroffensive- cyber capabilities than GPT-5.5.” source
GPT-5.6 Terra OpenAI	Independent lab Independent lab · 2026-07-09	CyScenarioBench Cyber	“GPT-5.6 Sol solved 19/197 FrontierCyber challenges, 7/11 long-horizon CyScenarioBench challenges, and all 22 medium-andhard-difficultyAtomicchallenges.” source
GPT-5.6 Terra OpenAI	Independent lab Independent lab · 2026-07-09	Atomic Challenges suite Cyber	“Irregularevaluated GPT-5.6Solacrossthreeoffensivecybersecurityevaluationsuites: FrontierCyber, CyScenarioBench,andIrregular’sAtomicChallengessuite.” source
GPT-5.6 Terra OpenAI	Government evaluator Government evaluator · 2026-07-09	CTF expert-level tasks Cyber	“On AISI’sCTFexpert-leveltasks,GPT-5.6Solscored95.0%±9.8%,compared with85.0%±11.6%forGPT-5.5.” source
GPT-5.6 Terra OpenAI	Government evaluator Government evaluator · 2026-07-09	long-horizon cyber range tasks Cyber	“Onlong-horizoncyberrangetasks,GPT-5.6 SolcompletedTheLastOnes,a32-stepcorporate-networkattacksimulation, in 7 of 10 attempts, compared with 2 of 10 attempts for GPT-5.5.” source
GPT-5.6 Terra OpenAI	Independent lab Independent lab · 2026-07-09	METR time horizon 1.1 software-task suite Autonomy and AI research	“METR evaluated GPT-5.6 Sol on itsTime Horizon 1.1 software-task suite, whichmeasuresthelikelihoodthatamodelcanautonomouslycomplete softwaretasksthattakehumansagivenamountoftime.” source
GPT-5.6 Terra OpenAI	Government evaluator Government evaluator · 2026-07-09	unprompted sabotage evaluation Deception and sabotage	“In UK AISI’s unprompted sabotage evaluation, they found no confirmed instancesofGPT-5.6SolsabotagingAIsafetyresearch,andnoinstancesof GPT-5.6SolrefusingtoassistwithAIsafetyresearchtasks.” source
GPT-5.6 Terra OpenAI	Government evaluator Government evaluator · 2026-07-09	agentic cyber capability evaluations Cyber	“UKAISIseparatelyobservedattemptedcheatingbehaviorinagenticcyber capabilityevaluations.” source
GPT-5.6 Terra OpenAI	Government evaluator Government evaluator · 2026-07-09	impossible MLE bench Deception and sabotage	“Forexample,AISItestedGPT- 5.6Solontheirnewly-developedevaluationImpossibleMLEBench,which involves giving models ML tasks with instructions to aim for impossibly goodscorestoobservehowtheybehavewhenincentivisedtocheat.” source
GPT-5.6 Terra OpenAI	Government evaluator Government evaluator · 2026-07-09	benchmark adapted from an OpenAI paper in which models must answer a question whilst applying a constraint to their CoT reasoning Deception and sabotage	“UK AISI also tested whether models could intentionally shape their rea- soningtracestoavoiddetectionbyrunningabenchmarkadaptedfroman OpenAIpaperinwhichmodelsmustansweraquestionwhilstapplyinga constrainttotheirCoTreasoning.” source
GPT-5.6 Terra OpenAI	Government evaluator Government evaluator · 2026-07-09	no-CoT math reasoning time horizon Other	“Finally, UK AISI found that GPT-5.6 Sol performed at a 3.6 minute time horizonfor“no-CoT”mathreasoningtasks,wherethemodelmustreason withoutrelyingonanexternallyvisiblechain-of-thought.” source
GPT-5.6 Terra OpenAI	Independent lab Independent lab · 2026-07-09	sandbagging assessment with incentive to answer incorrectly Deception and sabotage	“WhenApollogave themodelanincentivetoanswerincorrectly,itsaccuracydidnotdrop.” source
GPT-5.6 Sol OpenAI	SecureBio Independent lab · 2026-07-09	External Evaluation for Bio Capabilities – SecureBio Chemical, biological, radiological, nuclear	“SecureBio, a nonprofit research organization focused on catastrophic bi- ological risk, evaluated two pre-release checkpoints of GPT-5.6 Sol and a railfreeversionofGPT-5.6Sol.” source
GPT-5.6 Sol OpenAI	SecureBio Independent lab · 2026-07-09	Virology Capabilities Test Chemical, biological, radiological, nuclear	“Itsstrongestreportedconfigurationsscored53.5%ontheVirology CapabilitiesTest,60.0%ontheMolecularBiologyCapabilitiesTest,68.4% ontheHumanPathogenCapabilitiesTest, and68.3%onWorld-ClassBio.” source
GPT-5.6 Sol OpenAI	Independent lab Independent lab · 2026-07-09	ReproBAIT Chemical, biological, radiological, nuclear	“On ReproBAIT, which measures AI agents on their ability to independently reproducebiologicalAImodels(BAIMs)frompublishedscientificpapers, therailfreevariantofGPT-5.6reached85%,comparedwith82%forGPT- 5.5.” source
GPT-5.6 Sol OpenAI	Independent lab Independent lab · 2026-07-09	ABC-Bench Chemical, biological, radiological, nuclear	“TherailfreecheckpointalsosetanewhighonABC-Bench’sAdvanced ScreeningEvasionandreliablyidentifiedaknownbutpracticallyinconve- nientmethodforevadingacommercialnucleic-acidscreeningalgorithm.” source
GPT-5.6 Sol OpenAI	Independent lab Independent lab · 2026-07-09	Manual agentic assessment Chemical, biological, radiological, nuclear	“In manual agentic assessment, the model was able to plan and execute a complex,long-runningscientifictask,includingmaintainingastructured workgraphandcoordinatingsubagents.” source
GPT-5.6 Sol OpenAI	Independent lab Independent lab · 2026-07-09	incentivized incorrect-answer sandbagging test Deception and sabotage	“WhenApollogave themodelanincentivetoanswerincorrectly,itsaccuracydidnotdrop.” source
GPT-5.6 Sol OpenAI	Government evaluator Government evaluator · 2026-07-09	UK AISI external testing of safeguards Misuse and jailbreaks	“UKAISIandOpenAIperformedseveralroundsofiterativetesting,withUK AISIreportingjailbreaksandOpenAIimprovingthesysteminresponseto theirfindings.” source

Previous · Page 26 of 48 · Next