Gemini 3.1 Pro · SciCode(Scientific research coding) 59% · 附件证据(eval-scicode-launch)

Gemini 3.1 Pro 的 SciCode · Scientific research coding 官方出处。Gemini 3.1 Pro Thinking (High) · 59%。见《Gemini 3.1 Pro Model Evaluation — launch-day version》PDF p.3, results table, SciCode row, Gemini 3.1 Pro Thinking (High) column。证据 eval-scicode-launch。

原文与定位

Gemini 3.1 Pro · SciCode(Scientific research coding),Gemini 3.1 Pro Thinking (High)配置,Accuracy 59%(具体成绩公布时间未确认)。见《Gemini 3.1 Pro Model Evaluation — launch-day version》PDF p.3, results table, SciCode row, Gemini 3.1 Pro Thinking (High) column。 查看成绩条件

SciCode / Gemini 3.1 Pro Thinking (High): 59%
官方材料
Gemini 3.1 Pro Model Evaluation — launch-day version · PDF 第 3 页
定位
附件 · PDF p.3, results table, SciCode row, Gemini 3.1 Pro Thinking (High) column
材料版本
3-page evaluation PDF archived 2026-02-19 16:22:46 UTC; separate from current methodology revision.
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
已实际下载官方PDF首发当天回放 https://web.archive.org/web/20260219162246id_/https://storage.googleapis.com/deepmind-media/gemini/gemini_3-1_pro_model_evaluation.pdf;Memento-Datetime Thu, 19 Feb 2026 16:22:46 GMT。3页全文已核读,p.3主表实际渲染核查;与当前版本的差异为SWE-bench Pro方法新增based on the public set and字样,原始分数未变。
引用文本

Gemini 3.1 Pro · SciCode(Scientific research coding),Gemini 3.1 Pro Thinking (High)配置,Accuracy 59%(具体成绩公布时间未确认)。官方出处 Gemini 3.1 Pro Model Evaluation — launch-day version(附件,3-page evaluation PDF archived 2026-02-19 16:22:46 UTC; separate from current methodology revision.)PDF p.3, results table, SciCode row, Gemini 3.1 Pro Thinking (High) column,https://web.archive.org/web/20260219162246id_/https://storage.googleapis.com/deepmind-media/gemini/gemini_3-1_pro_model_evaluation.pdf#page=3。Benchlog https://benchlog.lekshome.cc/evidence/gemini-3-1-pro/eval-scicode-launch/

关联成绩与条件

Gemini 3.1 Pro · SciCode 成绩与配置
指标与成绩配置与评测条件证据关系
Accuracy59%原文 59% · 单位 %
公布 未确认
Gemini 3.1 Pro Thinking (High)
设置
Gemini API model id gemini-3.1-pro-preview; default sampling settings; evaluation table column specifies Thinking (High). All scores are pass@1 except where noted.
未知项
Exact thinking budget and sampling parameters are not listed.
工具
工具条件未记录
推理预算
high
框架
未记录
协议
Result sourced from Artificial Analysis.
条件
Scientific research coding.

直接支持该成绩

在排名中查看此成绩