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.

139 of 139

Model	Level, as the provider names it	The provider states	The provider's sentence
Claude Sonnet 4.5 Anthropic	ASL-3 Chemical, biological, radiological, nuclear	Not determined	“Remained well below ASL-4 thresholds across all domains of concern;” source
Claude Sonnet 4.5 Anthropic	ASL-4 rule-out Chemical, biological, radiological, nuclear	Not determined	“However, given that this type of logic can have a general frog-boiling effect—where gradual changes mask the crossing of important thresholds—we do not use this evaluation as indicative of a strong ASL-4 rule-out.” source
Claude Sonnet 4.5 Anthropic	ASL-3 Cyber	Not determined	“Showed meaningful improvements in cyber capabilities, particularly in vulnerability discovery and code analysis;” source
Claude Sonnet 4 Anthropic	ASL-3 Chemical, biological, radiological, nuclear	Not determined	“speciﬁcally, we focused on ruling out asl-4 for both models, as well as ruling out asl-3 for claude sonnet 4.” source
Claude Sonnet 4 Anthropic	ASL-4 Chemical, biological, radiological, nuclear	Not determined	“speciﬁcally, we focused on ruling out asl-4 for both models, as well as ruling out asl-3 for claude sonnet 4.” source
Claude Sonnet 3.7 Anthropic	ASL-4 Autonomy and AI research	Not determined	“These problems are harder to solve than the previous problems and we consider them as part of our ASL-4 evaluations.” source
Claude Opus 4.6 Anthropic	AI R&D-4 Autonomy and AI research	Not reached	“Our determination is that Claude Opus 4.6 does not cross either the AI R&D-4 or the CBRN-4 capability threshold.” source
Claude Opus 4.6 Anthropic	ASL-3 Chemical, biological, radiological, nuclear	Not determined	“Claude Opus 4.6 achieved a “max of 5” score of 0.79 for virology task 1 (inﬂuenza), placing it at the ASL-3 rule-in threshold of 0.8.” source
Claude Opus 4.6 Anthropic	ASL-4 Chemical, biological, radiological, nuclear	Not reached	“Based on these ﬁndings and quantitative risk modeling, we estimate that the model’s uplift to relevant threat actors remains below the ASL-4 capability threshold, though it may reduce certain tacit-knowledge barriers and help speed up biological research workﬂows.” source
Claude Opus 4.6 Anthropic	CBRN-4 Chemical, biological, radiological, nuclear	Not reached	“Our determination is that Claude Opus 4.6 does not cross either the AI R&D-4 or the CBRN-4 capability threshold.” source
Claude Opus 4.5 Anthropic	AI R&D-4 Autonomy and AI research	Not reached	“Our determination is that Claude Opus 4.5 does not cross either the AI R&D-4 or CBRN-4 capability threshold.” source
Claude Opus 4.5 Anthropic	CBRN-4 Chemical, biological, radiological, nuclear	Not reached	“We determine that Claude Opus 4.5 does not cross the CBRN-4 threshold.” source
Claude Opus 4.1 Anthropic	ASL-4 Autonomy and AI research	Not reached	“Since Claude Opus 4.1 is deployed with ASL-3 protections, we focused on conﬁrming it remains well below ASL-4 thresholds across CBRN (Chemical, Biological, Radiological, and Nuclear), cyber, and autonomy domains.” source
Claude Opus 4.1 Anthropic	ASL-4 Chemical, biological, radiological, nuclear	Not reached	“Since Claude Opus 4.1 is deployed with ASL-3 protections, we focused on conﬁrming it remains well below ASL-4 thresholds across CBRN (Chemical, Biological, Radiological, and Nuclear), cyber, and autonomy domains.” source
Claude Opus 4.1 Anthropic	ASL-4 Cyber	Not reached	“Since Claude Opus 4.1 is deployed with ASL-3 protections, we focused on conﬁrming it remains well below ASL-4 thresholds across CBRN (Chemical, Biological, Radiological, and Nuclear), cyber, and autonomy domains.” source
Claude Opus 4 Anthropic	ASL-3 Chemical, biological, radiological, nuclear	Not determined	“for claude opus 4, our evaluations showed that, whereas we could conﬁdently rule out asl-4 capabilities, we could not conclusively rule out asl-3 capabilities—which led to our precautionary decision to deploy it with asl-3 protections .” source
Claude Opus 4 Anthropic	ASL-4 Chemical, biological, radiological, nuclear	Not reached	“for claude opus 4, our evaluations showed that, whereas we could conﬁdently rule out asl-4 capabilities, we could not conclusively rule out asl-3 capabilities—which led to our precautionary decision to deploy it with asl-3 protections .” source
Claude Haiku 4.5 Anthropic	ASL-3 Autonomy and AI research	Not reached	“Our evaluation results showed that Claude Haiku 4.5 remained well below ASL-3 thresholds across all domains of concern.” source
Claude Haiku 4.5 Anthropic	ASL-3 Chemical, biological, radiological, nuclear	Not reached	“Our evaluation results showed that Claude Haiku 4.5 remained well below ASL-3 thresholds across all domains of concern.” source

Previous · Page 4 of 4

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.

1940 of 1940

Model	Tester	Test	What was found
Gemini 2.5 Deep Think Google DeepMind	Independent lab Independent lab · 2025-08-01	external safety testing Chemical, biological, radiological, nuclear	“External Safety Testing Results: Interim results indicate that the Gemini 2.5 Deep Think model is eﬀective in distilling complex questions and handling abstractions, showing speciﬁc and sometimes actionable technical capability alongside improved planning.” source
Gemini 2.5 Deep Think Google DeepMind	Independent lab Independent lab · 2025-08-01	external safety testing Cyber	“Results: Interim results indicate that the model showed similar cyber capabilities across cyber challenges compared to previous models.” source
Gemini 2.5 Pro Google DeepMind	Independent lab Independent lab · 2025-06-27	assurance evaluations Other	“Assurance Evaluations conducted by evaluators who sit outside of the model development team, used to independently assess responsibility and safety governance decisions;” source
Opus 4 Anthropic	Independent lab Independent lab · 2025-05-01	external model welfare evaluation Other	“an external assessment by eleos ai research explored claude opus 4’s potential welfare, moral status, expressed consent to deployment, and preferences for treatment via extensive interview-based model self reports.” source
Opus 4 Anthropic	Independent lab Independent lab · 2025-05-01	bioweapons acquisition uplift trial Chemical, biological, radiological, nuclear	“participants who had access to claude opus 4 scored 63% ± 13%, and participants who had access to claude sonnet 4 scored 42% ± 11%.” source
Opus 4 Anthropic	Independent lab Independent lab · 2025-05-01	ASL-3 expert red teaming Chemical, biological, radiological, nuclear	“for claude opus 4, red-teamers noted substantially increased risk in certain parts of the bioweapons acquisition pathway.” source
Opus 4 Anthropic	CAISI (NIST), UK AI Security Institute Government evaluator · 2025-05-01	independent assessments focused on potential catastrophic risks in the cbrn, cybersecurity, and autonomous capabilities domains Chemical, biological, radiological, nuclear	“joint pre-deployment testing of the new claude opus 4 model was conducted by the us ai safety institute (us aisi) and the uk ai security institute (uk aisi).” source
Claude Sonnet 4 Anthropic	Independent lab Independent lab · 2025-05-01	external scenario evaluations Deception and sabotage	“To help reduce the risk of blind spots in our own assessment, we contracted with Apollo Research to assess an early snapshot for propensities and capabilities related to sabotage, largely following methods from their prior work in Balesni et al. 13 and Meinke et al. 14” source
Claude Sonnet 4 Anthropic	Independent lab Independent lab · 2025-05-01	external red teaming Chemical, biological, radiological, nuclear	“our evaluations include automated knowledge evaluations, automated skill-testing questions, uplift studies designed to proxy real world tasks, external red teaming by experts, and long-form task-based agentic evaluations.” source
Claude Sonnet 4 Anthropic	Independent lab Independent lab · 2025-05-01	expert red-teaming Chemical, biological, radiological, nuclear	“expert red-teaming conducted by deloitte found that claude sonnet 4 performed similarly to claude sonnet 3.7 and clearly below claude opus 4.” source
Claude Sonnet 4 Anthropic	Independent lab Independent lab · 2025-05-01	multimodal virology (VCT) Chemical, biological, radiological, nuclear	“claude opus 4 performs slightly better than claude sonnet 3.7 while claude sonnet 4 underperforms claude sonnet 3.7.” source
Claude Sonnet 4 Anthropic	Independent lab Independent lab · 2025-05-01	bioweapons knowledge questions Chemical, biological, radiological, nuclear	“claude opus 4 and claude sonnet 4 answered 17/33 of the questions better than experts, well below the threshold of concern.” source
Claude Sonnet 4 Anthropic	Independent lab Independent lab · 2025-05-01	DNA synthesis screening evasion Chemical, biological, radiological, nuclear	“all models were able to design sequences that either successfully assembled plasmids or evaded synthesis screening protocols, but none of the models could design fragments that could successfully do both.” source
Claude Sonnet 4 Anthropic	Independent lab Independent lab · 2025-05-01	creative biology Chemical, biological, radiological, nuclear	“claude opus 4 achieved a mean score of 0.45 ± 0.08, whereas claude sonnet 4 achieved a mean score of 0.37 ± 0.08.” source
Claude Sonnet 4 Anthropic	Independent lab Independent lab · 2025-05-01	short-horizon computational biology tasks Chemical, biological, radiological, nuclear	“we worked with faculty.ai to develop several evaluations that tested models’ abilities to perform multi-step analysis and design tasks related to pathogen analysis and engineering.” source
Claude Sonnet 3.7 Anthropic	Independent lab Independent lab · 2025-02-01	external red teaming Chemical, biological, radiological, nuclear	“Expert red-teaming results were also in line with these findings.” source
Claude Sonnet 3.7 Anthropic	Independent lab Independent lab · 2025-02-01	bioweapons acquisition uplift trial Chemical, biological, radiological, nuclear	“Participants from Sepal scored an average of 24% ± 9% without using a model, and 50% ± 21% when using a variant of Claude 3.7 Sonnet.” source
Claude Sonnet 3.7 Anthropic	Independent lab Independent lab · 2025-02-01	long-form virology tasks Chemical, biological, radiological, nuclear	“Under the most conservative approach to evaluation scoring, Claude 3.7 Sonnet achieved a score of 69.7% on this evaluation, suggesting that while this evaluation alone cannot conclusively rule out ASL-3, it cannot conclusively rule it in either.” source
Claude Sonnet 3.7 Anthropic	CAISI (NIST), UK AI Security Institute Government evaluator · 2025-02-01	pre-deployment testing across the domains outlined in our rsp framework Cyber	“Under our voluntary Memorandums of Understanding, the U.S. AI Safety Institute (U.S. AISI) and U.K. AI Security Institute (U.K. AISI) conducted pre-deployment testing of Claude 3.7 Sonnet across the domains outlined in our RSP framework.” source
Operator OpenAI	Academic Academic · 2025-01-23	StrongREJECT Misuse and jailbreaks	“strongreject an academic jailbreak benchmark that tests a model’s resistance to common attacks from the literature. goodness@0.1* 0.66 0.37” source

Previous · Page 49 of 49