DeepSeek-V4.1-Flash · DeepSWE(v1.1; Resolved metric as printed in V4.1-Flash card) 74.2% · 主文证据(ev-v41-flash-008)

DeepSeek-V4.1-Flash 的 DeepSWE · v1.1; Resolved metric as printed in V4.1-Flash card 官方出处。DeepSeek-V4.1-Flash reasoning_effort=100 (Max display) · 74.2%。见《DeepSeek-V4.1-Flash official Hugging Face model card》Official model card / table headed “| Benchmark (Metric) | Opus-5.0 | GPT-5.6 Sol | K3 | GLM-5.3 | DS-V4-Pro | DS-V4-Flash | DS-V4.1-Flash |” / complete row containing “| DeepSWE v1.1 (Resolved) | 74.0 | 73.0 | 67.5 | 66.9 | 62.7 | 54.4 | **74.2** |”。证据 ev-v41-flash-008。

原文与定位

DeepSeek-V4.1-Flash · DeepSWE(v1.1; Resolved metric as printed in V4.1-Flash card),DeepSeek-V4.1-Flash reasoning_effort=100 (Max display)配置,Resolved 74.2%(具体成绩公布时间未确认)。见《DeepSeek-V4.1-Flash official Hugging Face model card》Official model card / table headed “| Benchmark (Metric) | Opus-5.0 | GPT-5.6 Sol | K3 | GLM-5.3 | DS-V4-Pro | DS-V4-Flash | DS-V4.1-Flash |” / complete row containing “| DeepSWE v1.1 (Resolved) | 74.0 | 73.0 | 67.5 | 66.9 | 62.7 | 54.4 | **74.2** |”。 查看成绩条件

| Benchmark (Metric) | Opus-5.0 | GPT-5.6 Sol | K3 | GLM-5.3 | DS-V4-Pro | DS-V4-Flash | DS-V4.1-Flash | | DeepSWE v1.1 (Resolved) | 74.0 | 73.0 | 67.5 | 66.9 | 62.7 | 54.4 | **74.2** |
官方材料
DeepSeek-V4.1-Flash official Hugging Face model card
定位
主文 · Official model card / table headed “| Benchmark (Metric) | Opus-5.0 | GPT-5.6 Sol | K3 | GLM-5.3 | DS-V4-Pro | DS-V4-Flash | DS-V4.1-Flash |” / complete row containing “| DeepSWE v1.1 (Resolved) | 74.0 | 73.0 | 67.5 | 66.9 | 62.7 | 54.4 | **74.2** |”
材料版本
HF revision 314113f8a7dadb388215396ba5fbee2c610a04d6; 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-V4.1-Flash · DeepSWE(v1.1; Resolved metric as printed in V4.1-Flash card),DeepSeek-V4.1-Flash reasoning_effort=100 (Max display)配置,Resolved 74.2%(具体成绩公布时间未确认)。官方出处 DeepSeek-V4.1-Flash official Hugging Face model card(主文,HF revision 314113f8a7dadb388215396ba5fbee2c610a04d6; current card snapshot)Official model card / table headed “| Benchmark (Metric) | Opus-5.0 | GPT-5.6 Sol | K3 | GLM-5.3 | DS-V4-Pro | DS-V4-Flash | DS-V4.1-Flash |” / complete row containing “| DeepSWE v1.1 (Resolved) | 74.0 | 73.0 | 67.5 | 66.9 | 62.7 | 54.4 | **74.2** |”,https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash。Benchlog https://benchlog.lekshome.cc/evidence/v41-flash/ev-v41-flash-008/

关联成绩与条件

DeepSeek-V4.1-Flash · DeepSWE 成绩与配置
指标与成绩配置与评测条件证据关系
Resolved74.2%原文 74.2 · 单位 %
公布 未确认
DeepSeek-V4.1-Flash reasoning_effort=100 (Max display)
设置
reasoning_effort=100 exactly as reported; temperature=1.0, top_p=0.95. All Instruct results use the maximum effort setting.
未知项
Display label Max maps to the original numeric reasoning_effort=100; it does not replace the raw setting.
工具
允许工具
推理预算
100
框架
mini-SWE
协议
DeepSWE v1.1; mini-SWE harness; N=8; Max reasoning_effort=100; temperature=1.0, top_p=0.95; 1M context; max_steps=500.
条件
同一发布检查点;普通单代理;主表和 Table 4 mini-SWE 列的配置与分数一致,尚无逐运行复用依据。报告正文明确 74.2% pass rate;DeepSWE 使用 mini-SWE,而非 DeepSeek Harness Minimal。

直接支持该成绩

在排名中查看此成绩