Gemini 2.5 Pro (GA) · ZeroBench(Average over 4 runs) 4.5% · 附件证据(hist-t3-zerobench)
Gemini 2.5 Pro (GA) 的 ZeroBench · Average over 4 runs 官方出处。Gemini 2.5 Pro stable API · 4.5%。见《Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities — launch-day 70-page version》Historical PDF p.12, Table 3, ZeroBench row, Gemini 2.5 Pro column。证据 hist-t3-zerobench。
原文与定位
Gemini 2.5 Pro (GA) · ZeroBench(Average over 4 runs),Gemini 2.5 Pro stable API配置,Judge score 4.5%(具体成绩公布时间未确认)。见《Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities — launch-day 70-page version》Historical PDF p.12, Table 3, ZeroBench row, Gemini 2.5 Pro column。 查看成绩条件
Gemini 2.5 Pro / zerobench: 4.5%. Gemini used as judge; average over 4 runs.
- 官方材料
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities — launch-day 70-page version · PDF 第 12 页
- 定位
- 附件 · Historical PDF p.12, Table 3, ZeroBench row, Gemini 2.5 Pro column
- 材料版本
- 70-page PDF, archived capture from 2025-06-17; cover dated 2025-06-17
- 版本公布
- 未确认
- 披露时间
- · 已有首发依据
- 采集时间
- 历史依据
- 已实际下载首发当天官方PDF回放 https://web.archive.org/web/20250617164147id_/https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf;Memento-Datetime Tue, 17 Jun 2025 16:41:47 GMT。70/70页全文、安全章节及附录已核读,成绩表和图表已视觉核查;与现行73页版分开保存。
引用文本
Gemini 2.5 Pro (GA) · ZeroBench(Average over 4 runs),Gemini 2.5 Pro stable API配置,Judge score 4.5%(具体成绩公布时间未确认)。官方出处 Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities — launch-day 70-page version(附件,70-page PDF, archived capture from 2025-06-17; cover dated 2025-06-17)Historical PDF p.12, Table 3, ZeroBench row, Gemini 2.5 Pro column,https://web.archive.org/web/20250617164147id_/https://storage.googleapis.com/deepmind-media/gemini/gemini_v2_5_report.pdf#page=12。Benchlog https://benchlog.lekshome.cc/evidence/gemini-2-5-pro/hist-t3-zerobench/
关联成绩与条件
| 指标与成绩 | 配置与评测条件 | 证据关系 |
|---|---|---|
| Judge score4.5%原文 4.5% · 单位 % 公布 未确认 | Gemini 2.5 Pro stable API
| 直接支持该成绩 在排名中查看此成绩 |