Unverified50% confidenceBenchmarkExact time
OpenAI's GPT-6 Astra system card reports a 99.99% defense rate against direct injection, but attackers still achieved an 8.5% success rate in Gray Swan's external indirect injection arena.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/12/2026
First Seen
Valid until: 1/10/2027
Sources
Related Entities
Related Claims
UnverifiedIn a test involving an unfamiliar game with no manual or rules, the previous generation of AI scored 7.8%, while GPT-6 achieved 99.9% under an agent framework that retains reasoning state.66% similarUnverifiedGPT-6 Astra achieved a near-perfect score of 99.9% on ARC-AGI-type tests, while the average score of ordinary human test-takers was only 48%.63% similarUnverifiedOpenAI defense factory real-world metrics: dynamic validation reduced the false positive rate to below 1%, attribution assignment accuracy was approximately 90%, and the fix rollback rate was below 1%.61% similarUnverifiedAccording to the technical report, when instructed to evade, Astra can reduce the detection rate of OpenAI's chain-of-thought monitor to below 11%.61% similarUnverifiedEven GPT-4-level Agents often achieve end-to-end success rates below 60% on complex tasks involving more than 5 tool calls.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1003810API
curl https://kongchang.com/api/v1/knowledge/claims/1003810MCP
get_claim(id=1003810)