Unverified50% confidenceFactExact time
参与测试的是Codex/GPT系列和Opus系列的代表性智能体系统
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/14/2026
First Seen
Valid until: 12/13/2026
Sources
Related Entities
Related Claims
UnverifiedOpenAI的GPT系列以版本号区分能力代际，o系列专注于强化推理能力，Codex、DALL·E、Whisper等是功能专项模型74% similarUnverifiedThe benchmark tested leading AI models including Claude, GPT series, and Gemini.71% similarUnverifiedCodex's underlying model is the GPT series, which has unique advantages in creative generation and UI design71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/921077API
curl https://kongchang.com/api/v1/knowledge/claims/921077MCP
get_claim(id=921077)