Unverified50% confidenceBenchmarkExact time
在 DeepSWE 1.1 测试中,GPT-6.1 Sol 得 75.2%,Astra 为 74.8%,Cloud Sonnet 5.5 为 71.0%,GPT-6 Sol 最高 68.8%
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/30/2026
First Seen
Valid until: 12/29/2026
Sources
Related Entities
Related Claims
UnverifiedGPT-6.1 Sol的API输入和输出token标准价格仅为Astra的五分之一78% similarUnverified在DeepSWE基准测试中,GPT 5.5以约70%的通过率高居榜首,比Opus 4.7领先超过15个百分点75% similarUnverifiedGPT-5.6 Sol在BrowseComp浏览任务基准上达到92.2%75% similarUnverifiedGPT-6.1 Sol缺少公开的基准测试数据来支撑其接近Astra智能的说法73% similarVerifiedGPT-5.6 Sol在ARC-AGI-2上取得92.5%的成绩73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/961315API
curl https://kongchang.com/api/v1/knowledge/claims/961315MCP
get_claim(id=961315)