Partially Verified70% confidenceBenchmarkExact time
Gemini 4 Argon在Deep7e长流程软件工程测试中取得77.9%的新记录,超越Claude Opus 5.5
4
Sources
70%
Confidence
Short-term (~14 days)
Relevance
10/1/2026
First Seen
Valid until: 10/15/2026
Sources
Related Entities
Related Claims
UnverifiedGoogle报告Gemini 4 Argon在DeepSWE 1.1软件工程评测中获得77.9%的成绩(厂商自行公布)78% similarPartially Verified在 Automation Bench 上 Gemini 4 Argon 得分 51.3%,超过 Fable 5.1 的 31.4% 和 Opus 5.5 的 42.5%73% similarUnverifiedGemini 4 Argon 在 LV Bench(视频/长内容理解)上得分 91%,刷新纪录71% similarPartially VerifiedGemini 4 Argon的最大输出从64000 Token提高到100万(指输出上限而非上下文窗口)70% similarUnverifiedGemini 4 Argon宣称支持100万token的输出能力70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/963816API
curl https://kongchang.com/api/v1/knowledge/claims/963816MCP
get_claim(id=963816)