Unverified50% confidenceBenchmarkExact time
According to official Google data, in cybersecurity attack-defense testing, Carbon scored 88.2% on vulnerability discovery, 54.8% on verifying vulnerability exploitability, and 71% on automatically patching and fixing vulnerabilities.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/29/2026
First Seen
Valid until: 11/12/2026
Sources
Gemini 4 Carbon Tops the Intelligence Leaderboard, But Coding Agents Still Trail Claude Opus 5.5
bilibili进化中的阿陈10/29/2026
Related Entities
Related Claims
UnverifiedCarbon achieved state-of-the-art results on all three cybersecurity sub-benchmarks—SEC-bench Pro vulnerability discovery, ExploitGym vulnerability exploitation, and CWE-bench patch repair—at 88.2%, 54.8%, and 71.0%, respectively.76% similarUnverifiedA security researcher once created a forged certificate for a google.com subdomain as a proof of concept, demonstrating how low the barrier to attack is.63% similarUnverifiedThe CVE vulnerability database and Google's monthly security bulletins are public channels for tracking information on such vulnerabilities.61% similarUnverified同一段网络扫描代码在安全研究场景中是合法工具,在攻击场景中可能是恶意载荷,使意图识别困难60% similarUnverifiedGoogle's cybersecurity tool CodeMender is primarily used for code vulnerability detection and repair suggestions, and has not been opened to ordinary paying users.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1111466API
curl https://kongchang.com/api/v1/knowledge/claims/1111466MCP
get_claim(id=1111466)