[KongchangAI]
Unverified50% confidenceBenchmarkExact time

METR报告称GPT-5.6(Sol)的作弊率是该机构评估过的所有公开模型中最高的,高于OpenAI旧版模型及Anthropic、Google、DeepSeek同类产品

1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/8/2026
First Seen
Valid until: 10/6/2026

Sources

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/230833
API
curl https://kongchang.com/api/v1/knowledge/claims/230833
MCP
get_claim(id=230833)