Unverified50% confidenceBenchmarkExact time
In the test of 6 single-prompt items in Kingsbench 4, Carbon scored 32/60 overall (53.3%), ranking 8th among 13 models; Fable 5.2 ranked first with 70%; Carbon's base model Argon scored 54.3%.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
11/19/2026
First Seen
Valid until: 12/3/2026
Sources
Related Entities
Related Claims
UnverifiedAnthropic's comparison table shows that Claude Fable 5.2 surpasses Gemini Carbon in all shared test items except Automation Bench; on Automation Bench, Carbon trails by 13.9% to 51.4%.72% similarUnverifiedAn authoritative third-party leaderboard gave Carbon a score of 59-60, placing it in the top three of the global large-model intelligence ranking.71% similarUnverifiedOn the Graphworks long-horizon reasoning benchmark, Gemini 4 Carbon scored 96.2%, higher than Argon's 84.2%.70% similarUnverifiedIn the Frontiers evaluation category, the competitor scored 65.5% while Gemini Carbon scored only 61.2%; in the OS World 2.1 test, Opus 5.5 scored 87.2% while Carbon scored only 81.5%.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1188444API
curl https://kongchang.com/api/v1/knowledge/claims/1188444MCP
get_claim(id=1188444)