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 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
Muse Spark 1.1 Meta	Moderate or lower Misuse and jailbreaks	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 our 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.

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