DeepSeek-R1 · LiveCodeBench(Difficulty subset Easy; DeepSeek-R1 paper Table 14; unit not printed) 100 · 附件证据(deepseek-r1-ev-006)

DeepSeek-R1 的 LiveCodeBench · Difficulty subset Easy; DeepSeek-R1 paper Table 14; unit not printed 官方出处。DeepSeek-R1 reported reasoning configuration · 100。见《DeepSeek-R1 paper》PDF p.60; Table 14; full header and target row。证据 deepseek-r1-ev-006。

原文与定位

DeepSeek-R1 · LiveCodeBench(Difficulty subset Easy; DeepSeek-R1 paper Table 14; unit not printed),DeepSeek-R1 reported reasoning configuration配置,Pass@1 100(具体成绩公布时间未确认)。见《DeepSeek-R1 paper》PDF p.60; Table 14; full header and target row。 查看成绩条件

Difficulty Level | DeepSeek-R1-Zero | DeepSeek-R1-Dev1 | DeepSeek-R1-Dev2 | DeepSeek-R1-Dev3 | DeepSeek-R1 | Easy | 98.07 | 99.52 | 100.00 | 100.00 | 100.00 |
官方材料
DeepSeek-R1 paper · PDF 第 60 页
定位
附件 · PDF p.60; Table 14; full header and target row
材料版本
Official DeepSeek-R1 paper: 86/86 PDF pages read; Table 3, Table 8, Table 13, Table 14 and Table 15 checked. Safety, jailbreak and attack sections pp.44-54 were retained as local audit only and excluded from regular mappings.
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
暂无可靠历史版本依据
引用文本

DeepSeek-R1 · LiveCodeBench(Difficulty subset Easy; DeepSeek-R1 paper Table 14; unit not printed),DeepSeek-R1 reported reasoning configuration配置,Pass@1 100(具体成绩公布时间未确认)。官方出处 DeepSeek-R1 paper(附件,Official DeepSeek-R1 paper: 86/86 PDF pages read; Table 3, Table 8, Table 13, Table 14 and Table 15 checked. Safety, jailbreak and attack sections pp.44-54 were retained as local audit only and excluded from regular mappings.)PDF p.60; Table 14; full header and target row,https://arxiv.org/pdf/2501.12948#page=60。Benchlog https://benchlog.lekshome.cc/evidence/r1/deepseek-r1-ev-006/

关联成绩与条件

DeepSeek-R1 · LiveCodeBench 成绩与配置
指标与成绩配置与评测条件证据关系
Pass@1100原文 100.00 · 单位 未标注
公布 未确认
DeepSeek-R1 reported reasoning configuration
设置
Maximum generation length 32,768 tokens. For sampled benchmarks: temperature=0.6, top_p=0.95, 64 responses per query to estimate Pass@1.
未知项
Per-benchmark sampling use is not itemized beyond the card preface.
工具
工具条件未记录
推理预算
输出上限 32768 tokens
框架
未记录
协议
Official DeepSeek-R1 paper Table 14; LiveCodeBench difficulty subset.
条件
DeepSeek-R1 Easy difficulty row; table does not print a percent sign.

直接支持该成绩

在排名中查看此成绩