Unverified50% confidenceBenchmarkExact time
On the Graphworks long-horizon reasoning benchmark, Gemini 4 Carbon scored 96.2%, higher than Argon's 84.2%.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/29/2026
First Seen
Valid until: 1/27/2027
Sources
Google Releases Gemini 4 Carbon: Security Agent Back on Top
bilibili大模型论文解读10/29/2026
Related Entities
Related Claims
UnverifiedOn the fifth edition of the Comprehensive Intelligence leaderboard, Gemini 4 Carbon scored 59 points, ranking first and overtaking Claude Opus 5.5, 9 points higher than Argon.80% similarUnverifiedOn RareBench, Gemini 4 Argon ranked first with a 57% assisted diagnosis rate, and scored 52.2% on LabBench wet-lab reasoning.70% similarUnverifiedIn the Exploit Gym test, Gemini 4 Carbon's success rate in verifying vulnerability exploitability was 54.8%.70% similarUnverifiedGemini 4 Carbon scored 59 on the Artificial Analysis Intelligence Index.70% similarUnverifiedIn Graphworks' 250,000 to 1 million token context test, Carbon's accuracy was 96.2%, while GPT-6 Astra's was 71.8%.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1111502API
curl https://kongchang.com/api/v1/knowledge/claims/1111502MCP
get_claim(id=1111502)