Unverified50% confidenceBenchmarkExact time

在Health Bench Professional上，Soul达到60.5分，比GPT-5.5高出8.7分

1

Sources

50%

Confidence

Medium-term (~90 days)

Relevance

7/8/2026

First Seen

Valid until: 10/6/2026

Sources

GPT-5.6发布：Soul/Terra/Luna三层布局，编排能力训入模型

bilibili杨博士说AI6/29/2026

Related Claims

Unverified在HealthBench Professional基准上Mythos 5得66.0%，GPT-5.6 Sol得60.5%（长度校正后约64%）73% similar Unverified在Agent's Last Exam基准测试中，GPT-5.6 Soul（extra high档）得分近54%，Fable（max档）为45%72% similar UnverifiedSoul标准模式得分88.8%，开启Ultra后跃升至91.9%，比Max模式多涨2.7个百分点68% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/248695

API

curl https://kongchang.com/api/v1/knowledge/claims/248695

MCP

get_claim(id=248695)