Unverified50% confidenceBenchmarkExact time
An authoritative third-party leaderboard gave Carbon a score of 59-60, placing it in the top three of the global large-model intelligence ranking.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
11/14/2026
First Seen
Valid until: 11/28/2026
Sources
Gemini 4 Hydrogen vs Carbon Hands-On: Can the Lightweight Model Beat the Flagship?
bilibili电子吕游11/14/2026
Related Entities
Related Claims
UnverifiedOn the Graphworks long-horizon reasoning benchmark, Gemini 4 Carbon scored 96.2%, higher than Argon's 84.2%.59% similarUnverifiedTop of the intelligence leaderboard: Claude Fable 5.2 Max ranks first with 65 points, Gemini 4 Carbon High second with 60 points, and Claude Opus 5.5 Max third with 59 points; among the open-source domestic camp, Kimi K3.1 Pro ranks 11th with 46 points.59% similarUnverifiedClaude Fable 5.2 Max scored 60% on CursorBench 4.0, second only to carbon high's 60.4%.58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1171279API
curl https://kongchang.com/api/v1/knowledge/claims/1171279MCP
get_claim(id=1171279)