Unverified50% confidenceBenchmarkExact time
GPT-6 Sol（索尔）在AA综合能力榜的Max档位下相比上一代Terra（泰拉）实现小幅领先，但与Astra之间仍有明显差距
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/28/2026
First Seen
Valid until: 12/27/2026
Sources
Related Entities
Related Claims
Unverified基准测试结果显示，Sol和Sol Ultra在大多数领域优于竞争对手Misos 5，Tara优于Fable 571% similarUnverified在DeepSuite基准上Grok 4.7得71%，GPT 5.6 Sol为72.7%，Fable 5.1为70%，Astra Max以74.1%登顶70% similarUnverified综合实测结果，四款模型能力排名为：Sol > GPT-5.5 > Terra > Luna69% similarUnverified在SWE-Bench Pro编程评测上，Claude Fable 5以80%的成绩领先GPT-5.6 Sol的64.6%69% similarUnverifiedGPT-5.6 Sol在Humanity's Last Exam取得最高分，且价格远低于Claude Opus和Fable68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/954922API
curl https://kongchang.com/api/v1/knowledge/claims/954922MCP
get_claim(id=954922)