DeepSeek-R1-Distill-Qwen-14B · Codeforces(Rating; contest snapshot unspecified; table does not print a percent sign) 1481 rating · 主文证据(ds-completion-r1-distill-qwen-14b-ev-006)

DeepSeek-R1-Distill-Qwen-14B 的 Codeforces · Rating; contest snapshot unspecified; table does not print a percent sign 官方出处。DeepSeek-R1-Distill-Qwen-14B · 1481 rating。见《DeepSeek-R1-Distill-Qwen-14B official Hugging Face model card》Official model card / table headed “| Model | AIME 2024 pass@1 | AIME 2024 cons@64 | MATH-500 pass@1 | GPQA Diamond pass@1 | LiveCodeBench pass@1 | CodeForces rating |” / complete row containing “| DeepSeek-R1-Distill-Qwen-14B | 69.7 | 80.0 | 93.9 | 59.1 | 53.1 | 1481 |”。证据 ds-completion-r1-distill-qwen-14b-ev-006。

原文与定位

DeepSeek-R1-Distill-Qwen-14B · Codeforces(Rating; contest snapshot unspecified; table does not print a percent sign),DeepSeek-R1-Distill-Qwen-14B配置,Rating 1481 rating(具体成绩公布时间未确认)。见《DeepSeek-R1-Distill-Qwen-14B official Hugging Face model card》Official model card / table headed “| Model | AIME 2024 pass@1 | AIME 2024 cons@64 | MATH-500 pass@1 | GPQA Diamond pass@1 | LiveCodeBench pass@1 | CodeForces rating |” / complete row containing “| DeepSeek-R1-Distill-Qwen-14B | 69.7 | 80.0 | 93.9 | 59.1 | 53.1 | 1481 |”。 查看成绩条件

| Model | AIME 2024 pass@1 | AIME 2024 cons@64 | MATH-500 pass@1 | GPQA Diamond pass@1 | LiveCodeBench pass@1 | CodeForces rating | | DeepSeek-R1-Distill-Qwen-14B | 69.7 | 80.0 | 93.9 | 59.1 | 53.1 | 1481 |
官方材料
DeepSeek-R1-Distill-Qwen-14B official Hugging Face model card
定位
主文 · Official model card / table headed “| Model | AIME 2024 pass@1 | AIME 2024 cons@64 | MATH-500 pass@1 | GPQA Diamond pass@1 | LiveCodeBench pass@1 | CodeForces rating |” / complete row containing “| DeepSeek-R1-Distill-Qwen-14B | 69.7 | 80.0 | 93.9 | 59.1 | 53.1 | 1481 |”
材料版本
HF revision 1df8507178afcc1bef68cd8c393f61a886323761; current card snapshot; full Markdown reviewed
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-Distill-Qwen-14B · Codeforces(Rating; contest snapshot unspecified; table does not print a percent sign),DeepSeek-R1-Distill-Qwen-14B配置,Rating 1481 rating(具体成绩公布时间未确认)。官方出处 DeepSeek-R1-Distill-Qwen-14B official Hugging Face model card(主文,HF revision 1df8507178afcc1bef68cd8c393f61a886323761; current card snapshot; full Markdown reviewed)Official model card / table headed “| Model | AIME 2024 pass@1 | AIME 2024 cons@64 | MATH-500 pass@1 | GPQA Diamond pass@1 | LiveCodeBench pass@1 | CodeForces rating |” / complete row containing “| DeepSeek-R1-Distill-Qwen-14B | 69.7 | 80.0 | 93.9 | 59.1 | 53.1 | 1481 |”,https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B。Benchlog https://benchlog.lekshome.cc/evidence/r1-distill-qwen-14b/ds-completion-r1-distill-qwen-14b-ev-006/

关联成绩与条件

DeepSeek-R1-Distill-Qwen-14B · Codeforces 成绩与配置
指标与成绩配置与评测条件证据关系
Rating1481 rating原文 1481 · 单位 rating
公布 未确认
DeepSeek-R1-Distill-Qwen-14B
设置
Distilled dense checkpoint; source card preface states max generation length 32,768 tokens, temperature=0.6, top_p=0.95, and 64 responses per query for sampled pass@1 estimates.
未知项
The source does not specify a separate effort value for each distilled checkpoint.
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
未说明
条件
Official distilled-model evaluation table; exact model scale retained in the release name and source row. The source table does not print a percent sign.

直接支持该成绩

在排名中查看此成绩