[KongchangAI]
Partially Verified80% confidenceBenchmarkExact time

三个 GPT-5.6 模型在长程代理微调任务上均拿满分 10 分,而 GPT-5.5 和 Opus 4.7 在该任务只能拿两三分

7
Sources
80%
Confidence
Medium-term (~90 days)
Relevance
7/10/2026
First Seen
Valid until: 10/8/2026

Sources

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/452869
API
curl https://kongchang.com/api/v1/knowledge/claims/452869
MCP
get_claim(id=452869)