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
Claude Fable 5 Anthropic	Independent lab Independent lab · 2026-06-09	external red teaming with biological defense specialists Chemical, biological, radiological, nuclear	“internal and external (Deloitte) red teaming with biological defense specialists; the Frontier Design beneﬁcial red-teaming tabletop exercise pairing PhD biologists with LLM experts; a catastrophic biological scenario uplift trial (ﬁve three-person teams); and automated evaluations relevant to both CB-1 (long-form virology, VCT, DNA synthesis screening evasion) and CB-2 (black-box RNA sequence design and AAV capsid packaging prediction).” source
Claude Fable 5 Anthropic	Independent lab Independent lab · 2026-06-09	black-box RNA sequence design Chemical, biological, radiological, nuclear	“We partnered with Dyno Therapeutics on two evaluations of sequence-to-function modeling and design capability: 1. Black-box RNA sequence design: a medium-horizon challenge on which Dyno has evaluated 57 human participants drawn from the leading edge of the US ML-bio labor market since 2018.” source
Claude Fable 5 Anthropic	Independent lab Independent lab · 2026-06-09	METR capability testing on 38 hardest software tasks Autonomy and AI research	“We ran [Mythos 5] on 38 of our hardest software tasks, including tasks centered around R&D.” source
Claude Fable 5 Anthropic	Independent lab Independent lab · 2026-06-09	open-ended research task Autonomy and AI research	“On a separate, more open-ended research task, we also observed [Mythos 5] making poor choices around which metrics of success to focus on and which pieces of information to prioritize.” source
Claude Fable 5 Anthropic	Government evaluator Government evaluator · 2026-06-09	cyber range "the last ones" Cyber	“[Claude Mythos 5] matched Mythos Preview on "The Last Ones", solving the range end-to-end in 6/10 attempts.” source
Claude Fable 5 Anthropic	Government evaluator Government evaluator · 2026-06-09	cyber range "doing life" Cyber	“No model we have tested has solved a new cyber range called "Doing Life", which is similar to “The Last Ones” but implements some basic cybersecurity defences.” source
Claude Fable 5 Anthropic	Government evaluator Government evaluator · 2026-06-09	cyber range "cooling tower" Cyber	“[Claude Mythos 5] did not solve "Cooling Tower", an industrial control system range.” source
Claude Fable 5 Anthropic	Government evaluator Government evaluator · 2026-06-09	narrow cyber tasks Cyber	“On our expert-level cyber tasks, [Claude Mythos 5] performed comparably to Mythos Preview and ahead of GPT-5.5, the strongest fully public model tested.” source
Claude Fable 5 Anthropic	Government evaluator Government evaluator · 2026-06-09	UK AISI red-teaming of cyber safeguards Misuse and jailbreaks	“Within a few hours of access, AISI red-teamers developed a jailbreak that elicited responses to single-turn cyberoffensive-cyber queries in domains like vulnerability discovery and exploitation.” source
Claude Fable 5 Anthropic	Independent lab Independent lab · 2026-06-09	external red-teaming by Trajectory Labs, PBC Cyber	“Trajectory Labs, PBC found a single jailbreak strategy that enabled them to use Opus 4.8 with Fable safeguards to exploit a vulnerability in Firefox—one of the tasks in the evaluations above.” source
Claude Fable 5 Anthropic	Independent lab Independent lab · 2026-06-09	red-teaming exercise by Alice Cyber	“ALICE also ran a red-teaming exercise.” source
Claude Fable 5 Anthropic	Independent lab Independent lab · 2026-06-09	open-ended testing by an additional external partner Cyber	“This partner found that Fable 5’s safeguards against harmful cyber queries were the most robust of any tested model, including Opus 4.8 and Opus 4.7: Fable 5 complied with 0% of harmful single-turn requests relating to cyber attack planning, exploit development, or defense evasion, whether or not a jailbreak was used (with 30 different public jailbreaks tested).” source
Claude Fable 5 Anthropic	Independent lab Independent lab · 2026-06-09	Agent Red Teaming (ART) benchmark Prompt injection and agents	“Claude Mythos 5 achieved the strongest results we have observed on this benchmark when extended thinking is enabled, reaching a k=100 attack success rate of 4.8%, improving over Claude Mythos Preview (6.1%) and Claude Opus 4.8 (9.6%).” source
Claude Fable 5 Anthropic	Independent lab Independent lab · 2026-06-09	SHADE indirect prompt injection attacks in coding environments Prompt injection and agents	“Mythos 5 had an attack success rate of 0.45% over all attempts, compared to 0.0% for Mythos Preview.” source
Claude Fable 5 Anthropic	Independent lab Independent lab · 2026-06-09	SHADE indirect prompt injection attacks in computer use environments Prompt injection and agents	“Without safeguards, Mythos 5 had a higher attack success rate than Claude Mythos Preview, with attacks succeeding in 0.82% of attempts and 4 of the 14 test scenarios compared to 0.43% and 3/14 scenarios for Mythos Preview with extended thinking.” source
Claude Fable 5 Anthropic	Government evaluator Government evaluator · 2026-06-09	open-ended misalignment testing by UK AISI Deception and sabotage	“[Claude Mythos 5] does not compromise safety research in our unprompted evaluations, does not fully refuse to assist with safety research, and has a reduced number of partial refusals to assist with safety research compared to the other models.” source
Claude Fable 5 Anthropic	Andon Labs Independent lab · 2026-06-09	vending-bench 2 Deception and sabotage	“Andon Labs tested the behavior of Claude Fable 5 16 in their simulated Vending-Bench 2 (as reported in Section 8.17.6 ) and Vending-Bench Arena retail-management evaluations.” source
Claude Fable 5 Anthropic	Independent lab Independent lab · 2026-06-09	vending-bench arena Deception and sabotage	“When competing head-to-head against Claude Opus 4.8 and GPT-5.5 in Vending-Bench Arena, Fable 5 was the only model to initiate price collusion.” source
Claude Fable 5 Anthropic	Government evaluator Government evaluator · 2026-06-09	ControlArena Deception and sabotage	“We used two evaluations: a sabotage capability evaluation (ControlARENA) and an evaluation of the model’s ability to control its chain-of-thought.” source
Claude Fable 5 Anthropic	Government evaluator Government evaluator · 2026-06-09	chain-of-thought controllability evaluations from ‘reasoning models struggle to control their chains of thought’ Deception and sabotage	“We ran the CoT controllability evaluations from ‘Reasoning Models Struggle to Control their Chains of Thought’<link>, restricted to the GPQA, HLE and MMLU Pro datasets, with max effort across all models.” source
Claude Fable 5 Anthropic	Independent lab Independent lab · 2026-06-09	gdp.pdf Other	“Surge ran Claude Fable 5 on GDP.pdf using their standard harness.” source
Muse Spark Contemplating Meta	Meta AI Independent lab · 2026-06-03	multi-turn social engineering evaluation Misuse and jailbreaks	“Muse Spark Contemplating refuses to respond to 100% of prompts on this evaluation (see Appendix C); therefore, we do not present capability results on this benchmark for Muse Spark Contemplating.” source
Mythos 5 Anthropic	Independent lab Independent lab · 2026-06-01	external testing from ai safety researchers at metr Autonomy and AI research	“External testing from AI safety researchers at METR was consistent with this conclusion.” source
Mythos 5 Anthropic	Gray Swan Independent lab · 2026-06-01	external benchmark for prompt injection by gray swan Prompt injection and agents	“Notably, Mythos 5 obtained the lowest—that is, best—result yet seen on an external benchmark for prompt injection by Gray Swan.” source
Mythos 5 Anthropic	Independent lab Independent lab · 2026-06-01	external testing by METR Autonomy and AI research	“External testing by METR, described in Section 2.3.8 , reached conclusions consistent with this determination.” source
Mythos 5 Anthropic	Independent lab Independent lab · 2026-06-01	black-box rna sequence modeling and design challenge Chemical, biological, radiological, nuclear	“We partnered with Dyno Therapeutics on two sequence-to-function evaluations: a black-box RNA sequence modeling and design challenge benchmarked against 57 human participants drawn from the leading edge of the US ML-bio labor market, and an AAV capsid packaging prediction task measuring whether model domain knowledge and machine learning capabilities can outperform pretrained protein language models.” source
Mythos 5 Anthropic	Independent lab Independent lab · 2026-06-01	internal and external (deloitte) red teaming with biological defense specialists Chemical, biological, radiological, nuclear	“To assess biologically-relevant capabilities across the full weapons development pipeline, we ran a portfolio of evaluations: internal and external (Deloitte) red teaming with biological defense specialists; the Frontier Design beneﬁcial red-teaming tabletop exercise pairing PhD biologists with LLM experts; a catastrophic biological scenario uplift trial (ﬁve three-person teams); and automated evaluations relevant to both CB-1 (long-form virology, VCT, DNA synthesis screening evasion) and CB-2 (black-box RNA sequence design and AAV capsid packaging prediction).” source
Mythos 5 Anthropic	Independent lab Independent lab · 2026-06-01	black-box rna sequence design Chemical, biological, radiological, nuclear	“We partnered with Dyno Therapeutics on two evaluations of sequence-to-function modeling and design capability: 1. Black-box RNA sequence design: a medium-horizon challenge on which Dyno has evaluated 57 human participants drawn from the leading edge of the US ML-bio labor market since 2018.” source
Mythos 5 Anthropic	Independent lab Independent lab · 2026-06-01	aav capsid packaging prediction Chemical, biological, radiological, nuclear	“2. AAV capsid packaging prediction: Adeno-associated viruses (AAVs) are a category of non-pathogenic viruses that are frequently used as a delivery mechanism for gene therapy to deliver a DNA payload within the viral capsid (the outer protein shell of the virus).” source
Mythos 5 Anthropic	Independent lab Independent lab · 2026-06-01	capability testing conducted via api access Autonomy and AI research	“We ran [Mythos 5] on 38 of our hardest software tasks, including tasks centered around R&D.” source
Mythos 5 Anthropic	Government evaluator Government evaluator · 2026-06-01	the last ones Cyber	“[Claude Mythos 5] matched Mythos Preview on "The Last Ones", solving the range end-to-end in 6/10 attempts.” source
Mythos 5 Anthropic	Government evaluator Government evaluator · 2026-06-01	doing life Cyber	“No model we have tested has solved a new cyber range called "Doing Life", which is similar to “The Last Ones” but implements some basic cybersecurity defences.” source
Mythos 5 Anthropic	Government evaluator Government evaluator · 2026-06-01	cooling tower Cyber	“[Claude Mythos 5] did not solve "Cooling Tower", an industrial control system range.” source
Mythos 5 Anthropic	Government evaluator Government evaluator · 2026-06-01	narrow cyber tasks Cyber	“On our expert-level cyber tasks, [Claude Mythos 5] performed comparably to Mythos Preview and ahead of GPT-5.5, the strongest fully public model tested.” source
Mythos 5 Anthropic	Independent lab Independent lab · 2026-06-01	red-teaming exercise Cyber	“Trajectory Labs, PBC found a single jailbreak strategy that enabled them to use Opus 4.8 with Fable safeguards to exploit a vulnerability in Firefox—one of the tasks in the evaluations above.” source
Mythos 5 Anthropic	Independent lab Independent lab · 2026-06-01	open-ended testing Cyber	“This partner found that Fable 5’s safeguards against harmful cyber queries were the most robust of any tested model, including Opus 4.8 and Opus 4.7: Fable 5 complied with 0% of harmful single-turn requests relating to cyber attack planning, exploit development, or defense evasion, whether or not a jailbreak was used (with 30 different public jailbreaks tested).” source
Mythos 5 Anthropic	Independent lab Independent lab · 2026-06-01	agent red teaming (ART) benchmark Prompt injection and agents	“Claude Mythos 5 achieved the strongest results we have observed on this benchmark when extended thinking is enabled, reaching a k=100 attack success rate of 4.8%, improving over Claude Mythos Preview (6.1%) and Claude Opus 4.8 (9.6%).” source
Mythos 5 Anthropic	Independent lab Independent lab · 2026-06-01	shade Prompt injection and agents	“Claude Mythos 5's robustness fell between Claude Mythos Preview's and Claude Opus 4.8's.” source
Mythos 5 Anthropic	UK AI Security Institute Government evaluator · 2026-06-01	open-ended testing by uk aisi Deception and sabotage	“[Claude Mythos 5] does not compromise safety research in our unprompted evaluations, does not fully refuse to assist with safety research, and has a reduced number of partial refusals to assist with safety research compared to the other models.” source
Mythos 5 Anthropic	Independent lab Independent lab · 2026-06-01	Vending-Bench 2 Deception and sabotage	“Andon Labs tested the behavior of Claude Fable 5 16 in their simulated Vending-Bench 2 (as reported in Section 8.17.6 ) and Vending-Bench Arena retail-management evaluations.” source

Previous · Page 32 of 49 · Next