DeepSeek-V4-Flash-0731 · DeepSWE(Version/metric unspecified in V4-0813/0731 cards) 54.4 · 主文证据(ev-v4-flash-0731-003)

DeepSeek-V4-Flash-0731 的 DeepSWE · Version/metric unspecified in V4-0813/0731 cards 官方出处。DeepSeek-V4-Flash-0731, max reasoning effort · 54.4。见《DeepSeek-V4-Flash-0731 official Hugging Face model card》Official model card / table headed “| Benchmark | DeepSeek-V4-Flash-0731 | DeepSeek-V4-Flash (Preview) | DeepSeek-V4-Pro (Preview) | GLM-5.2 | Opus-4.8 |” / complete row containing “| DeepSWE | 54.4 | 7.3 | 12.8 | 46.2 | 58.0 |”。证据 ev-v4-flash-0731-003。

原文与定位

DeepSeek-V4-Flash-0731 · DeepSWE(Version/metric unspecified in V4-0813/0731 cards),DeepSeek-V4-Flash-0731, max reasoning effort配置,Reported score 54.4(具体成绩公布时间未确认)。见《DeepSeek-V4-Flash-0731 official Hugging Face model card》Official model card / table headed “| Benchmark | DeepSeek-V4-Flash-0731 | DeepSeek-V4-Flash (Preview) | DeepSeek-V4-Pro (Preview) | GLM-5.2 | Opus-4.8 |” / complete row containing “| DeepSWE | 54.4 | 7.3 | 12.8 | 46.2 | 58.0 |”。 查看成绩条件

| Benchmark | DeepSeek-V4-Flash-0731 | DeepSeek-V4-Flash (Preview) | DeepSeek-V4-Pro (Preview) | GLM-5.2 | Opus-4.8 | | DeepSWE | 54.4 | 7.3 | 12.8 | 46.2 | 58.0 |
官方材料
DeepSeek-V4-Flash-0731 official Hugging Face model card
定位
主文 · Official model card / table headed “| Benchmark | DeepSeek-V4-Flash-0731 | DeepSeek-V4-Flash (Preview) | DeepSeek-V4-Pro (Preview) | GLM-5.2 | Opus-4.8 |” / complete row containing “| DeepSWE | 54.4 | 7.3 | 12.8 | 46.2 | 58.0 |”
材料版本
HF revision 7872f01b1d1fe23eabc4c98b48bffcef5a386062; current card snapshot
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-V4-Flash-0731 · DeepSWE(Version/metric unspecified in V4-0813/0731 cards),DeepSeek-V4-Flash-0731, max reasoning effort配置,Reported score 54.4(具体成绩公布时间未确认)。官方出处 DeepSeek-V4-Flash-0731 official Hugging Face model card(主文,HF revision 7872f01b1d1fe23eabc4c98b48bffcef5a386062; current card snapshot)Official model card / table headed “| Benchmark | DeepSeek-V4-Flash-0731 | DeepSeek-V4-Flash (Preview) | DeepSeek-V4-Pro (Preview) | GLM-5.2 | Opus-4.8 |” / complete row containing “| DeepSWE | 54.4 | 7.3 | 12.8 | 46.2 | 58.0 |”,https://huggingface.co/deepseek-ai/DeepSeek-V4-Flash-0731。Benchlog https://benchlog.lekshome.cc/evidence/deepseek-v4-flash-0731/ev-v4-flash-0731-003/

关联成绩与条件

DeepSeek-V4-Flash-0731 · DeepSWE 成绩与配置
指标与成绩配置与评测条件证据关系
Reported score54.4原文 54.4 · 单位 未标注
公布 未确认
DeepSeek-V4-Flash-0731, max reasoning effort
设置
The card identifies Max reasoning effort and DeepSeek Harness Minimal mode for code-agent evaluations; temperature=1.0 and top_p=0.95.
未知项
Effort and harness applicability is only asserted for the card-defined code-agent/public rows.
工具
工具条件未记录
推理预算
max
框架
DeepSeek Harness Minimal
协议
For code-agent public benchmark rows, card note: DeepSeek Harness Minimal, max reasoning effort, temperature=1.0, top_p=0.95.
条件
The card does not print a metric for this row. It is retained as a reported score without merging with a Pass@1 or other metric.

直接支持该成绩

在排名中查看此成绩