Unverified50% confidenceBenchmarkExact time
On the complex business and knowledge work benchmark leaderboard, Carbon scored 1609 points, more than 120 points above Argon's 1483 points, but it ranked below models such as Kimi and Grok.
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
UnverifiedIn 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%.70% similarUnverifiedCompared with Argon, Carbon's unsupported claims are reduced by about 2 times, overly overreaching behavior is reduced by 26%, and under-serving is reduced by 29%.59% similarUnverifiedArgon reportedly achieved nearly 78% on an authoritative software engineering benchmark.57% similarUnverifiedWith a 128K token context window, Argon scored 99.7% and Fable 91.4%; with a 1 million token context, Argon scored 84.2% and Fable 65.0%.57% similarUnverifiedIn the coding category, Argon won real-world coding (77.9% vs. 67.4%) and vibe coding (91.9% vs. 90.3%), ending in an overall 2-to-2 tie.56% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1111472API
curl https://kongchang.com/api/v1/knowledge/claims/1111472MCP
get_claim(id=1111472)