Unverified50% confidenceBenchmarkExact time
In the system test simulating a human operating a computer, Claude Opus 5.5 scored 87.2% and Carbon scored 81.5%.
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
UnverifiedOpus 5.5 achieved 81.8% on the Computer Use benchmark, slightly above Fable 5.1's 80.7%.67% similarUnverifiedOn the coding Agent index, Carbon's 59 points is lower than Claude Code with Opus 5.5's 62 points.65% similarUnverifiedIn the official internal comparison table, Carbon surpasses Argon on all 17 benchmark tests; the terminal capability test rose from 57.1% to 65.2%, and the software engineering cleanup test rose from 4.3% to 9.6%.64% similarUnverifiedCarbon scored 59 on the Artificial Analysis Intelligence Index 5.00, ranking first globally.62% similarUnverifiedCarbon reached 96.2% in the Graphworks ultra-long-context test, more than 30 points ahead of its competitors.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1111469API
curl https://kongchang.com/api/v1/knowledge/claims/1111469MCP
get_claim(id=1111469)