跳到主要内容
综合下跌 严重度 10/10 2026-W22

Gemini 2.5 Pro 代码执行 (v5) 下跌 19.5 分

Gemini 2.5 Pro Run #131

分数对比

维度 上期 本期 变化
主榜 (v5) 67.0 47.7 -19.3
代码执行 (v5) 88.2 56.3 -31.9
知识综合 (v5) 55.8 42.3 -13.5
材料约束 (v5) 79.3 53.0 -26.3
性价比 38.1 26.3 -11.8
稳定性 34.3 35.3 +1
可用性 100.0 76.0 -24

受影响维度

代码执行 (v5) -33.4
材料约束 (v5) -29
可用性 -24
性价比 -12.1
知识综合 (v5) -9.4
稳定性 -2.4

丢分题目 Top 5

#1 CSV 单行解析 execution 100 0 -100 严格
模型原始回复(截取)
[API ERROR] Your project has exceeded its monthly spending cap. Please go to AI Studio at https://ai.studio/spend to manage your project spend cap. Learn more at https://ai.google.dev/gemini-api/docs/billing#project-spend-caps. 
#2 Debug:Webhook 幂等处理 execution 100 0 -100 严格
模型原始回复(截取)
[API ERROR] Your project has exceeded its monthly spending cap. Please go to AI Studio at https://ai.studio/spend to manage your project spend cap. Learn more at https://ai.google.dev/gemini-api/docs/billing#project-spend-caps. 
#3 稳定去重:字典列表 execution 100 0 -100 严格
模型原始回复(截取)
[API ERROR] Your project has exceeded its monthly spending cap. Please go to AI Studio at https://ai.studio/spend to manage your project spend cap. Learn more at https://ai.google.dev/gemini-api/docs/billing#project-spend-caps. 
#4 手机号规范化 execution 100 0 -100 严格
模型原始回复(截取)
[API ERROR] Your project has exceeded its monthly spending cap. Please go to AI Studio at https://ai.studio/spend to manage your project spend cap. Learn more at https://ai.google.dev/gemini-api/docs/billing#project-spend-caps. 
#5 两年 TCO 计算 grounding 88 0 -88 严格
模型原始回复(截取)
[API ERROR] Your project has exceeded its monthly spending cap. Please go to AI Studio at https://ai.studio/spend to manage your project spend cap. Learn more at https://ai.google.dev/gemini-api/docs/billing#project-spend-caps. 
Run #131 · 公式 v7 · 判分 v6 · 题库 v6 · 2026-05-25 04:16 SGT
查看 Gemini 2.5 Pro 完整档案