Expired50% confidenceFactExact time
Gemini 2.5 Pro scored only 11.7 on visual score and 22.6 on functional score for full-stack website tasks.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026(expired)
Sources
Tsinghua and Zhipu Release Full-Stack Web Dev Benchmark: Top AI Models Fail Spectacularly
bilibili跟我学一辈子AI吧5/22/2026
Related Claims
UnverifiedGemini 2.5 Pro's visual score drops to 11.7 and functionality score drops to 22.6 on full-stack web development tasks.83% similarUnverifiedGemini 2.5 Pro's score dropped by more than 60% from static webpage tasks to full-stack tasks.78% similarUnverifiedGemini 2.5 Pro scores approximately 63 on static web page generation tasks in the benchmark.76% similarUnverifiedGemini 2.5 Pro experienced a cliff-like score drop from approximately 63 on static pages to 11.7 visual score on full-stack tasks, representing a drop of over 80%.73% similarUnverifiedGemini 2.5 Pro scored 18.8% on the Humanities Last Exam benchmark, far exceeding O3 Mini's 14% and other models' scores below 10%.72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/51768API
curl https://kongchang.com/api/v1/knowledge/claims/51768MCP
get_claim(id=51768)