Gemini 3 Pro · ScreenSpot-Pro(1,581 expert-annotated tasks across 23 professional applications and 3 operating systems) 72.7% · 附件证据(eval-screenspot-extra-high)
Gemini 3 Pro 的 ScreenSpot-Pro · 1,581 expert-annotated tasks across 23 professional applications and 3 operating systems 官方出处。ScreenSpot-Pro · extra_high(材料称coming soon) · 72.7%。见《Gemini 3 Pro - Evaluations Approach, Methodology & Results》PDF p.3, results table, ScreenSpot-Pro row, Gemini 3 Pro column。证据 eval-screenspot-extra-high。
原文与定位
Gemini 3 Pro · ScreenSpot-Pro(1,581 expert-annotated tasks across 23 professional applications and 3 operating systems),ScreenSpot-Pro · extra_high(材料称coming soon)配置,Accuracy 72.7%(具体成绩公布时间未确认)。见《Gemini 3 Pro - Evaluations Approach, Methodology & Results》PDF p.3, results table, ScreenSpot-Pro row, Gemini 3 Pro column。 查看成绩条件
ScreenSpot-Pro / Gemini 3 Pro: 72.7%
- 官方材料
- Gemini 3 Pro - Evaluations Approach, Methodology & Results · PDF 第 3 页
- 定位
- 附件 · PDF p.3, results table, ScreenSpot-Pro row, Gemini 3 Pro column
- 材料版本
- 3-page evaluation PDF; results as of November 2025
- 版本公布
- 未确认
- 披露时间
- 未确认 · 首发/后补未确认
- 采集时间
- 历史依据
- 已实际取得首发当天官方PDF历史回放 https://web.archive.org/web/20251118163819id_/https://storage.googleapis.com/deepmind-media/gemini/gemini_3_pro_model_evaluation.pdf;回放原件与已完整核读的当前PDF完全相同。原件及响应记录:本轮整合目录 gemini-3-evaluation-historical-cdn.pdf。
引用文本
Gemini 3 Pro · ScreenSpot-Pro(1,581 expert-annotated tasks across 23 professional applications and 3 operating systems),ScreenSpot-Pro · extra_high(材料称coming soon)配置,Accuracy 72.7%(具体成绩公布时间未确认)。官方出处 Gemini 3 Pro - Evaluations Approach, Methodology & Results(附件,3-page evaluation PDF; results as of November 2025)PDF p.3, results table, ScreenSpot-Pro row, Gemini 3 Pro column,https://deepmind.google/models/evals-methodology/gemini-3-pro#page=3。Benchlog https://benchlog.lekshome.cc/evidence/gemini-3-pro/eval-screenspot-extra-high/
关联成绩与条件
| 指标与成绩 | 配置与评测条件 | 证据关系 |
|---|---|---|
| Accuracy72.7%原文 72.7% · 单位 % 公布 未确认 | ScreenSpot-Pro · extra_high(材料称coming soon)
| 直接支持该成绩 |