DeepSeek-R1 · 官方评测披露
DeepSeek-R1 当前收录 27 项测试的官方记录。已完成列明材料的核查。
模型发布 · DeepSeek R1
官方材料与核查范围
All listed official model-card, official News/API, metadata and directly linked technical-report materials for this release were read through the requested scope. Tables without an explicit unit retain an empty unit; figures without exact labels were not estimated. 核对时间 。
当前资料不足以还原首发。 No reliable historical snapshot proving the complete launch-day material set was obtained. Official publication dates and current materials do not substitute for a launch snapshot.
- DeepSeek-R1 official Hugging Face model card · 主文 · HF revision 56d4cbbb4d29f4355bab4b9a39ccb717a14ad5ad; current card snapshot公布 未确认 · 采集 · 已核查 Official model-card Markdown read in full; benchmark rows, notes, configuration statements and linked reports checked.
- DeepSeek-R1 official Hugging Face model metadata · 主文 · author=deepseek-ai; repo createdAt=2025-01-20T03:46:07.000Z (repository upload time only); lastModified=2025-03-27T04:01:59.000Z; sha=56d4cbbb4d29f4355bab4b9a39ccb717a14ad5ad公布 未确认 · 采集 · 已核查 Official model API metadata checked for author, repository identity, revision and timestamps; createdAt was never used as release date.
- DeepSeek-R1 发布,性能对标 OpenAI o1 正式版 · 主文 · Official DeepSeek News index entry dated 2025-01-20; index downloaded and retained locally公布 · 采集 · 已核查 The official dated entry or current service table was read for this release scope; aliases were not treated as weight checkpoints.
- 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.公布 未确认 · 采集 · 已核查 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.
配置
- DeepSeek-R1 reported reasoning configuration · Maximum generation length 32,768 tokens. For sampled benchmarks: temperature=0.6, top_p=0.95, 64 responses per query to estimate Pass@1. 输出上限 32768 tokens未知项 Per-benchmark sampling use is not itemized beyond the card preface.
直接前代与后续发布
当前收录未确认直接前代。 官方关系依据
测试记录 · 27
- MMLU · Version unspecified; Pass@1本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- MMLU-Redux · Version unspecified; Exact Match本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- MMLU-Pro · DeepSeek card version unspecified; Exact Match本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- DROP · Version unspecified; 3-shot F1本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- GPQA Diamond · Diamond subset; task snapshot unspecified本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- SimpleQA · Version unspecified; Correct metric本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- FRAMES · Version unspecified; Accuracy本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- LiveCodeBench · Version unspecified; Pass@1-CoT本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- Codeforces · Rating; contest snapshot unspecified本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- SWE-bench Verified · Agent mode; task snapshot unspecified本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- Aider-Polyglot · Version unspecified; Accuracy本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- AIME · 2024 edition; Pass@1本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- MATH-500 · 500-question set; Pass@1本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- CNMO · 2024 edition; Pass@1本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- C-Eval · Version unspecified; Exact Match本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- C-SimpleQA · Version unspecified; Correct metric本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- IF-Eval · DeepSeek-R1 paper Table 3; IF-Eval (PromptStrict); unit not printed本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- AlpacaEval 2.0 · DeepSeek-R1 paper Table 3; AlpacaEval 2.0 (LC-winrate); unit not printed本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- Arena-Hard · DeepSeek-R1 paper Table 3; Arena-Hard (GPT-4-1106); unit not printed本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- Codeforces · DeepSeek-R1 paper Table 3; Codeforces (Percentile); unit not printed本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- CLUEWSC · DeepSeek-R1 paper Table 3; CLUEWSC (EM); unit not printed (ds-completion-r1-cluewsc-em)本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- LiveCodeBench · Difficulty subset Easy; DeepSeek-R1 paper Table 14; unit not printed本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- LiveCodeBench · Difficulty subset Medium; DeepSeek-R1 paper Table 14; unit not printed本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- LiveCodeBench · Difficulty subset Hard; DeepSeek-R1 paper Table 14; unit not printed本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- AIME · 2025; Pass@1; DeepSeek-R1 paper Table 13 and accompanying prose本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- AMC 12 · 2024; DeepSeek-R1 paper Table 13本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)
- USAMO Index · 2025; AMC score + 10 × AIME score本次发布有 1 条成绩记录,含 1 条精确值(可含历史记录)