Expired50% confidenceEventExact time
All four AI models (ChatGPT 5.4, Gemini 3.1, DeepSeek V4 Pro, and Kimi 5.1) failed in the first round of a dynamic web scraping task targeting Baidu
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026(expired)
Sources
AI Coding Showdown: Four Major Models Show Shocking Performance Gaps on a Dynamic Web Scraping Task
bilibili图动中国6/11/2026
Related Claims
UnverifiedDeepSeek V4 Pro and Kimi 5.1 operated in Solid mode (autonomous completion of the entire workflow without human intervention), while ChatGPT 5.4 and Gemini 3.1 operated in standard interactive mode67% similarUnverified此前的PokeAgent挑战证明，即使是GPT-4V、Gemini等顶级多模态模型，在没有专门设计的辅助框架时，几乎无法在宝可梦RPG中取得任何进展67% similarUnverifiedThe frontend generation test also compared a suspected Gemini 3 refer model, Kimi KL, and Haiku 4.5, with GPT 5.1 leading in instruction following and visual quality.63% similarUnverifiedThis AI large model invocation website has integrated four models: Gemini, Tongyi Qianwen, DeepSeek, and Doubao.62% similarUnverifiedThere is no unified standard for version number naming in the AI industry; for example, Google's Gemini .5 versions are actually major architectural upgrades.61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/48432API
curl https://kongchang.com/api/v1/knowledge/claims/48432MCP
get_claim(id=48432)