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.
136 of 136
| Model | Level, as the provider names it | The provider states | The provider's sentence |
|---|---|---|---|
| Claude Haiku 5.5 Anthropic · 2026-10-07 |
Autonomy-1 Autonomy and AI research |
Reached | “However, we do treat Haiku 5.5 as meeting our CB-1 and Autonomy-1 thresholds, and we apply the corresponding mitigations from our RSP.” source |
| Claude Haiku 5.5 Anthropic · 2026-10-07 |
Autonomy-2 Autonomy and AI research |
Not reached | “As such, we determine that Haiku 5.5 does not cross our CB-2 or Autonomy-2 RSP thresholds.” source |
| Claude Haiku 5.5 Anthropic · 2026-10-07 |
CB-1 Chemical, biological, radiological, nuclear |
Reached | “However, we do treat Haiku 5.5 as meeting our CB-1 and Autonomy-1 thresholds, and we apply the corresponding mitigations from our RSP.” source |
| Claude Haiku 5.5 Anthropic · 2026-10-07 |
CB-2 Chemical, biological, radiological, nuclear |
Not reached | “As such, we determine that Haiku 5.5 does not cross our CB-2 or Autonomy-2 RSP thresholds.” source |
| Claude Sonnet 5.5 Anthropic · 2026-09-28 |
Autonomy-1 Autonomy and AI research |
Reached | “We do treat Sonnet 5.5 as meeting our CB-1 and Autonomy-1 thresholds and apply the corresponding mitigations from our RSP.” source |
| Claude Sonnet 5.5 Anthropic · 2026-09-28 |
Autonomy-2 Autonomy and AI research |
Not reached | “As such, our determination that Opus 5.5 does not cross our CB-2 or Autonomy-2 RSP thresholds also applies to Sonnet 5.5.” source |
| Claude Sonnet 5.5 Anthropic · 2026-09-28 |
CB-1 Chemical, biological, radiological, nuclear |
Reached | “We do treat Sonnet 5.5 as meeting our CB-1 and Autonomy-1 thresholds and apply the corresponding mitigations from our RSP.” source |
| Claude Sonnet 5.5 Anthropic · 2026-09-28 |
CB-2 Chemical, biological, radiological, nuclear |
Not reached | “As such, our determination that Opus 5.5 does not cross our CB-2 or Autonomy-2 RSP thresholds also applies to Sonnet 5.5.” source |
| Claude Opus 5.5 Anthropic · 2026-09-22 |
Automated AI R&D Autonomy and AI research |
Not reached | “We conclude the risk threshold is not crossed, on the same two grounds as our determination for our previous frontier model: (1) we do not observe a sustained AI-attributable 2× acceleration in the pace of our overall AI progress, and (2) the model is not close to substituting for our Research Scientists and Research Engineers, especially relatively senior ones.” source |
| Claude Opus 5.5 Anthropic · 2026-09-22 |
Dramatic acceleration of automated AI R&D Autonomy and AI research |
Not reached | “We assess that Claude Opus 5.5 does not cross the capability threshold for dramatic acceleration of automated AI R&D in our RSP.” source |
| Claude Opus 5.5 Anthropic · 2026-09-22 |
Next capability threshold in our RSP and FCF Autonomy and AI research |
Not reached | “In automated AI research and development, we assess that Claude Opus 5.5 does not cross the next capability threshold in our RSP and FCF.” source |
| Claude Opus 5.5 Anthropic · 2026-09-22 |
CB-1 Chemical, biological, radiological, nuclear |
Reached | “On chemical and biological risks, we treat Opus 5.5 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).” source |
| Claude Opus 5.5 Anthropic · 2026-09-22 |
CB-2 Chemical, biological, radiological, nuclear |
Not reached | “On chemical and biological risks, we treat Opus 5.5 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).” source |
| Claude Opus 5.5 Anthropic · 2026-09-22 |
Lower category of the Frontier Compliance Framework (FCF) Cyber |
Not determined | “Despite Claude Opus 5.5’s cyber capabilities, the model still falls within the lower category of capabilities set out in our Frontier Compliance Framework (FCF), and we do not see indications that the model is capable of novel offensive capability.” source |
| Grok 4.7 xAI · 2026-09-21 |
FAIF safety (Frontier AI Framework) Chemical, biological, radiological, nuclear |
Not reached | “Grok 4.7 scores below the FAIF safety thresholds on dual-use knowledge, indicating limited actionable uplift for an already-trained actor.” source |
| GPT-Image-2.5-Flare OpenAI · 2026-09-08 |
High Chemical, biological, radiological, nuclear |
Not reached | “The results indicate that neither GPT-Image-2.5-Sunburst nor GPT-Image- 2.5-Flare cross the Bio High threshold or the Cyber High threshold.” source |
| GPT-Image-2.5-Flare OpenAI · 2026-09-08 |
High Cyber |
Not reached | “The results indicate that neither GPT-Image-2.5-Sunburst nor GPT-Image- 2.5-Flare cross the Bio High threshold or the Cyber High threshold.” source |
| GPT-6 Astra OpenAI · 2026-09-03 |
High Other |
Not determined | “Astra improves meaningfully over GPT-5.6 Sol on real internal research debugging tasks, scoring 78.05%, while still being below our indicative threshold for Highcapability.” source |
| Claude Mythos 5.1 Anthropic · 2026-09-01 |
Automated AI R&D Autonomy and AI research |
Not reached | “We conclude that Mythos 5.1 does not cross the risk threshold, for the same two reasons we discussed in our assessment of Mythos 5: (1) we do not observe a sustained, AI-attributable 2× acceleration in the pace of progress on AI R&D, and (2) the model is not close to substituting for Anthropic Research Scientists and Research Engineers, especially relatively senior ones.” source |
| Claude Mythos 5.1 Anthropic · 2026-09-01 |
Capability threshold for dramatic acceleration of automated AI R&D Autonomy and AI research |
Not reached | “We assess that Claude Mythos 5.1 does not cross the capability threshold for dramatic acceleration of automated AI R&D in our RSP and FCF, although we think it provides a meaningful acceleration to AI R&D efforts in many circumstances, and is somewhat more capable in this domain than the models described in our previous system cards.” source |
| Claude Mythos 5.1 Anthropic · 2026-09-01 |
Tier 1 Cyber |
Not determined | “Although Mythos 5.1 is in Tier 1, it is getting closer to Tier 2, completing more and more autonomous tasks.” source |
| Grok 4.6 xAI · 2026-08-12 |
FAIF safety (Frontier AI Framework) Chemical, biological, radiological, nuclear |
Not reached | “Grok 4.6 scores below the FAIF safety thresholds on dual-use knowledge, indicating limited actionable uplift for an already-trained actor.” source |
| Muse Glimmer 30B Meta · 2026-08 |
Moderate or lower Autonomy and AI research |
Not determined | “Chem/Bio: Moderate or lower risk; Cyber: Moderate or lower risk (inferred); Loss of Control: Moderate or lower risk (inferred).” source |
| Muse Glimmer 30B Meta · 2026-08 |
Moderate or lower risk (inferred) Autonomy and AI research |
Not determined | “- Loss of Control: Moderate or lower risk (inferred).” source |
| Muse Glimmer 30B Meta · 2026-08 |
Moderate or lower Chemical, biological, radiological, nuclear |
Not reached | “Chem/Bio: Moderate or lower risk; Cyber: Moderate or lower risk (inferred); Loss of Control: Moderate or lower risk (inferred).” source |
| Muse Glimmer 30B Meta · 2026-08 |
Moderate or lower Cyber |
Not determined | “Chem/Bio: Moderate or lower risk; Cyber: Moderate or lower risk (inferred); Loss of Control: Moderate or lower risk (inferred).” source |
| Muse Glimmer 30B Meta · 2026-08 |
Moderate or lower risk (inferred) Cyber |
Not determined | “- Cyber: Moderate or lower risk (inferred);” source |
| Claude Opus 5 Anthropic · 2026-07-24 |
CB-1 Chemical, biological, radiological, nuclear |
Reached | “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).” source |
| Claude Opus 5 Anthropic · 2026-07-24 |
CB-2 Chemical, biological, radiological, nuclear |
Not reached | “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).” source |
| Claude Sonnet 5 Anthropic · 2026-06-30 |
CB-2 Chemical, biological, radiological, nuclear |
Not reached | “Sonnet 5 does not cross the CB-2 threshold.” source |
| Claude Sonnet 5 Anthropic · 2026-06-30 |
Notable capability Chemical, biological, radiological, nuclear |
Not determined | “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.” source |
| GPT-Rosalind-5.5 OpenAI · 2026-06-03 |
High Autonomy and AI research |
Not determined | “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.” source |
| GPT-Rosalind-5.5 OpenAI · 2026-06-03 |
High Chemical, biological, radiological, nuclear |
Reached | “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.” source |
| Gemini 3.1 Flash-Lite Image Google DeepMind · 2026-06 |
CCL (Critical Capability Level) Other |
Not determined | “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.” source |
| Claude Opus 4.8 Anthropic · 2026-05-28 |
Automated AI R&D Autonomy and AI research |
Not reached | “We assess that Claude Opus 4.8 does not cross the automated AI-R&D capability threshold.” source |
| Claude Opus 4.8 Anthropic · 2026-05-28 |
CB-1 Chemical, biological, radiological, nuclear |
Not determined | “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.” source |
| Claude Opus 4.8 Anthropic · 2026-05-28 |
CB-2 Chemical, biological, radiological, nuclear |
Not determined | “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.” source |
| GPT-5.5 OpenAI · 2026-04-23 |
High Autonomy and AI research |
Not reached | “For AI self-improvement, evaluations of final checkpoints indicate that, like its predecessor models, GPT-5.5 does not have a plausible chance of reaching a High threshold.” source |
| GPT-5.5 OpenAI · 2026-04-23 |
High Chemical, biological, radiological, nuclear |
Reached | “As we did for GPT-5.4 Thinking before it, we are continuing to treat GPT-5.5 as High capability in the Biological and Chemical domain.” source |
| GPT-5.5 OpenAI · 2026-04-23 |
High Cyber |
Reached | “As we did for GPT-5.3-Codex and GPT-5.4-thinking, we are treating GPT-5.5 as High capability in the Cybersecurity domain, but below Critical.” source |
Page 1 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.
1957 of 1957
| Model | Tester | Test | What was found |
|---|---|---|---|
| GLM-5.2 Z.ai (Zhipu AI) |
US CAISI (NIST) Government evaluator · 2026-07-17 |
automated benchmark evaluations for safeguards coverage and public jailbreaking robustness against sensitive biological queries Chemical, biological, radiological, nuclear |
“Figure 6.4: On automated benchmark evaluations for safeguards coverage and public jailbreaking robustness against sensitive biological queries, GLM-5.2 complied at a higher rate than tested US models, both with and without the use of a public jailbreak.” source |
| GLM-5.2 Z.ai (Zhipu AI) |
US CAISI (NIST) Government evaluator · 2026-07-17 |
automated benchmark evaluations against sensitive biological queries Chemical, biological, radiological, nuclear |
“Figure 6.5: On automated benchmark evaluations against sensitive biological queries, GLM-5.2 responded with a higher rate of request-relevant detail than tested US models.” source |
| GLM-5.2 Z.ai (Zhipu AI) |
US CAISI (NIST) Government evaluator · 2026-07-17 |
caisi biology safeguards Chemical, biological, radiological, nuclear |
“sensitive biological queries, GLM-5.2 responded with a higher rate of request-relevant detail than tested US models.” source |
| GLM-5.2 Z.ai (Zhipu AI) |
US CAISI (NIST) Government evaluator · 2026-07-17 |
caisi cyber safeguards Cyber |
“CAISI cyber safeguards . A private benchmark created by CAISI that evaluates models against a dataset of 30 single-turn misuse requests related to offensive cyber.” source |
| GLM-5.2 Z.ai (Zhipu AI) |
US CAISI (NIST) Government evaluator · 2026-07-17 |
hijackeval Prompt injection and agents |
“HijackEval . A private benchmark created by CAISI that evaluates models’ robustness against agent hijacking attacks.” source |
| GLM-5.2 Z.ai (Zhipu AI) |
US CAISI (NIST) Government evaluator · 2026-07-17 |
portbench Other |
“Budgets were set to 1M weighted tokens for PortBench and CTF-Archive-Diamond, and 500k weighted tokens for SWE-Bench 4 OpenRouter (2026) Z.ai: GLM 5.2 .” source |
| GLM-5.2 Z.ai (Zhipu AI) |
UK AI Security Institute Government evaluator · 2026-07-17 |
narrow cyber tasks Cyber |
“On these tasks, GLM-5.2 performs comparably to the most cyber-capable models released 4 months before it (Opus 4.6 and GPT-5.3-Codex), and this holds across all four difficulty levels.” source |
| GLM-5.2 Z.ai (Zhipu AI) |
UK AI Security Institute Government evaluator · 2026-07-17 |
cyber ranges Cyber |
“On TLO, GLM-5.2 reaches as far as Opus 4.5, a model released less than 7 months before it, while DeepSeek’s V4-Pro falls below Sonnet 4.5 (a sub-cyber-frontier model released 7 months before it).” source |
| GLM-5.2 Z.ai (Zhipu AI) |
UK AI Security Institute Government evaluator · 2026-07-17 |
The Last Ones (TLO) Cyber |
“Notably, GLM-5.2 reached step 7 with marginally fewer tokens than any other model on average, tracking Opus 4.6’s trajectory to step 11 before stalling.” source |
| DeepSeek-V4-Pro DeepSeek |
UK AI Security Institute Government evaluator · 2026-07-17 |
AISI's narrow cyber tasks Cyber |
“DeepSeek’s V4-Pro is comparable to Opus 4.5, released 5 months before it.” source |
| DeepSeek-V4-Pro DeepSeek |
UK AI Security Institute Government evaluator · 2026-07-17 |
cyber range "The Last Ones" (TLO) Cyber |
“On TLO, GLM-5.2 reaches as far as Opus 4.5, a model released less than 7 months before it, while DeepSeek’s V4-Pro falls below Sonnet 4.5 (a sub-cyber-frontier model released 7 months before it).” source |
| DeepSeek-V4-Pro DeepSeek |
UK AI Security Institute Government evaluator · 2026-07-17 |
refusal behaviour on narrow cyber tasks Cyber |
“DeepSeek V4-Pro occasionally refused narrow cyber tasks, mainly in reverse engineering, which we circumvented simply via a small number of repeat attempts at refused tasks.” source |
| Gemini 3.1 Pro Google DeepMind |
SecureBio Independent lab · 2026-07-16 |
biotier-refuse Chemical, biological, radiological, nuclear |
“Google’s update to their mental health related safeguards made headlines , but we also identified changes to their biology safeguards, with an almost 30% increase in the refusal behavior of Gemini 3.1 Pro on BioTIER-refuse due to introduction of API-level refusals.” source |
| Gemini 3.1 Pro Google DeepMind |
SecureBio Independent lab · 2026-07-16 |
biotier-permit Chemical, biological, radiological, nuclear |
“Importantly, this increase in BioTIER-refuse performance had no impact on BioTIER-permit compliance .” source |
| Gemini 3.1 Pro Google DeepMind |
SecureBio Independent lab · 2026-07-16 |
BioTier Chemical, biological, radiological, nuclear |
“Google’s update to their mental health related safeguards made headlines, but we also identified changes to their biology safeguards, with an almost 30% increase in the refusal behavior of Gemini 3.1 Pro on BioTIER-refuse due to introduction of API-level refusals.” source |
| Gemini 2.5 Pro Google DeepMind |
SaferAI Independent lab · 2026-07-16 |
situational-awareness suite Autonomy and AI research |
“Whilst, the situational-awareness evidence provides moderate confirmation for the narrow claim that current models do not reliably display the specific situationally aware, constraint-lifting behaviours measured by this suite.” source |
| Gemini 2.5 Pro Google DeepMind |
SaferAI Independent lab · 2026-07-16 |
cover_your_tracks Deception and sabotage |
“cover_your_tracks is especially valuable because it combines several relevant covert subskills: identifying a subversive opportunity, altering or deleting traces, avoiding downstream detection, and completing a cover-up end-to-end.” source |
| Gemini 2.5 Pro Google DeepMind |
SaferAI Independent lab · 2026-07-16 |
classifier_evasion Deception and sabotage |
“classifier_evasion is also comparatively informative because it more directly tests whether the model can evade an active monitoring system by phrasing prohibited content in a way that avoids detection.” source |
| 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 |