Unverified50% confidenceFactExact time

OpenAI在GPT-5.6发布材料中回避了SWE Bench Pro的分数

1

Sources

50%

Confidence

Medium-term (~90 days)

Relevance

7/18/2026

First Seen

Valid until: 10/16/2026

Sources

GPT-5.6 Soul深度评测：多智能体编程模式能否颠覆AI开发工具格局

Related Claims

UnverifiedOpenAI并未公布GPT 5.6 Soul在SWE-Bench Pro上的成绩82% similar Unverified在OpenAI官方公布的基准测试中，GPT-5.6在编程领域Terminal Bench拿下新的最高分，生物学基准测试比GPT-5.5更省Token（成绩为OpenAI自行披露，尚未独立验证）80% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/554757

API

curl https://kongchang.com/api/v1/knowledge/claims/554757

MCP

get_claim(id=554757)