DeepSeek-V4.1-Flash · ProgramBench(Metric Almost@1 as printed in V4.1-Flash card; task version unspecified) 20.3% · 主文证据(ev-v41-flash-009)

DeepSeek-V4.1-Flash 的 ProgramBench · Metric Almost@1 as printed in V4.1-Flash card; task version unspecified 官方出处。DeepSeek-V4.1-Flash reasoning_effort=100 (Max display) · 20.3%。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 “| ProgramBench (Almost@1) | **37.0** | 23.0 | 17.5 | 19.0 | 15.5 | — | 20.3 |”。证据 ev-v41-flash-009。

原文与定位

DeepSeek-V4.1-Flash · ProgramBench(Metric Almost@1 as printed in V4.1-Flash card; task version unspecified),DeepSeek-V4.1-Flash reasoning_effort=100 (Max display)配置,Almost@1 20.3%(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 “| ProgramBench (Almost@1) | **37.0** | 23.0 | 17.5 | 19.0 | 15.5 | — | 20.3 |”。 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 | | ProgramBench (Almost@1) | **37.0** | 23.0 | 17.5 | 19.0 | 15.5 | — | 20.3 |
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 “| ProgramBench (Almost@1) | **37.0** | 23.0 | 17.5 | 19.0 | 15.5 | — | 20.3 |”
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 · ProgramBench(Metric Almost@1 as printed in V4.1-Flash card; task version unspecified),DeepSeek-V4.1-Flash reasoning_effort=100 (Max display)配置,Almost@1 20.3%(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 “| ProgramBench (Almost@1) | **37.0** | 23.0 | 17.5 | 19.0 | 15.5 | — | 20.3 |”,https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash。Benchlog https://benchlog.lekshome.cc/evidence/v41-flash/ev-v41-flash-009/

关联成绩与条件

DeepSeek-V4.1-Flash · ProgramBench 成绩与配置
指标与成绩配置与评测条件证据关系
Almost@120.3%原文 20.3 · 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
工具条件未记录
推理预算
100
框架
DeepSeek Harness Minimal
协议
DeepSeek Harness Minimal; 1M context; temperature=1.0, top_p=0.95.
条件
Official Instruct comparison table; numeric effort=100 retained.

直接支持该成绩

在排名中查看此成绩