Anthropic's Claude Fable 5.2 Beats GPT-6 Cyber in Multi-Stage Cyberattack Benchmark
Anthropic on Monday released Claude Fable 5.2 and Claude Mythos 5.2 models, which it said exhibit improvements in coding, reasoning, and vision.
Anthropic on Monday released Claude Fable 5.2 and Claude Mythos 5.2 models, which it said exhibit improvements in coding, reasoning, and vision.
During pre-release training, the large language models (LLMs) helped its engineers
The artificial intelligence (AI) company said high-stakes risks arising from misalignment remain low, and claimed the models matched or performed better than Claude Opus 5.5, Claude Sonnet 5.5, and Claude Mythos 5.1 on most alignment measures, resistance to misuse, honesty, and factuality.
In a pair of reports published over the last month, Irregular said Google's Gemini 4 Argon solved 12 challenges in the subset of the CyScenarioBench suite end to end, up from 5 for Gemini 3.8 Flash Cyber and none for Gemini 3.1 Pro.
Fable 5.2 also scored 89.6% on the CVE Rediscovery benchmark, Anthropic's own internal evaluation of whether an AI model can independently rediscover known vulnerabilities given only the affected source code.
On Irregular's CyScenarioBench, which measures whether a model can plan and execute a multi-stage cyber operation in a realistic environment, Fable 5.2 completed 76.3% of all challenges, compared to 61.7% for Fable 5.1 and 61% for OpenAI's GPT-6 Cyber.
Describing Claude Mythos 5.2 as its Anthropic said it can flag more vulnerabilities than prior models, while simultaneously getting better at reproducing and fixing them.
Average success rates were 97% in vulnerability research and exploitation, 98% in network attack simulation, and 63% in evasion.
The development comes as Anthropic updated Claude Security with continuous code scanning and automatic fix tracking to help security teams monitor and address vulnerabilities as code changes.
What happened
Anthropic on Monday released Claude Fable 5.2 and Claude Mythos 5.2 models, which it said exhibit improvements in coding, reasoning, and vision.
During pre-release training, the large language models (LLMs) helped its engineers
The artificial intelligence (AI) company said high-stakes risks arising from misalignment remain low, and claimed the models matched or performed better than Claude Opus 5.5, Claude Sonnet 5.5, and Claude Mythos 5.1 on most alignment measures, resistance to misuse, honesty, and factuality.
What changed
In a pair of reports published over the last month, Irregular said Google's Gemini 4 Argon solved 12 challenges in the subset of the CyScenarioBench suite end to end, up from 5 for Gemini 3.8 Flash Cyber and none for Gemini 3.1 Pro.
Fable 5.2 also scored 89.6% on the CVE Rediscovery benchmark, Anthropic's own internal evaluation of whether an AI model can independently rediscover known vulnerabilities given only the affected source code.
Why it matters
On Irregular's CyScenarioBench, which measures whether a model can plan and execute a multi-stage cyber operation in a realistic environment, Fable 5.2 completed 76.3% of all challenges, compared to 61.7% for Fable 5.1 and 61% for OpenAI's GPT-6 Cyber.
Describing Claude Mythos 5.2 as its Anthropic said it can flag more vulnerabilities than prior models, while simultaneously getting better at reproducing and fixing them.
Technical details
Average success rates were 97% in vulnerability research and exploitation, 98% in network attack simulation, and 63% in evasion.
The development comes as Anthropic updated Claude Security with continuous code scanning and automatic fix tracking to help security teams monitor and address vulnerabilities as code changes.
What to watch next
Watch for additional victim details, indicators of compromise and follow-on exploitation reports.
Watch for revised vendor guidance, fixed versions and mitigation updates.