DeepSeek-V4.1-Flash-1017 · Humanity's Last Exam(V4.1-Flash-1017 comparison table; non-text-only value, metric/set unspecified) 42.6 · 主文证据(ev-v41-flash-1017-001)

DeepSeek-V4.1-Flash-1017 的 Humanity's Last Exam · V4.1-Flash-1017 comparison table; non-text-only value, metric/set unspecified 官方出处。DeepSeek-V4.1-Flash-1017 reported comparison · 42.6。见《DeepSeek-V4.1-Flash-1017 official Hugging Face model card》Official model card / table headed “| Benchmark | DS-V4.1-Flash-1017 | DS-V4.1-Flash | K3 | GLM-5.3 | GPT-5.6 Sol | Opus 5 |” / complete row containing “| HLE w/o tools | 42.6 (44.0†) | 36.8 (39.1†) | 43.5 | 42.0† | 44.5 | 56.3 |”。证据 ev-v41-flash-1017-001。

原文与定位

DeepSeek-V4.1-Flash-1017 · Humanity's Last Exam(V4.1-Flash-1017 comparison table; non-text-only value, metric/set unspecified),DeepSeek-V4.1-Flash-1017 reported comparison配置,Reported score 42.6(具体成绩公布时间未确认)。见《DeepSeek-V4.1-Flash-1017 official Hugging Face model card》Official model card / table headed “| Benchmark | DS-V4.1-Flash-1017 | DS-V4.1-Flash | K3 | GLM-5.3 | GPT-5.6 Sol | Opus 5 |” / complete row containing “| HLE w/o tools | 42.6 (44.0†) | 36.8 (39.1†) | 43.5 | 42.0† | 44.5 | 56.3 |”。 查看成绩条件

| Benchmark | DS-V4.1-Flash-1017 | DS-V4.1-Flash | K3 | GLM-5.3 | GPT-5.6 Sol | Opus 5 | | HLE w/o tools | 42.6 (44.0†) | 36.8 (39.1†) | 43.5 | 42.0† | 44.5 | 56.3 |
官方材料
DeepSeek-V4.1-Flash-1017 official Hugging Face model card
定位
主文 · Official model card / table headed “| Benchmark | DS-V4.1-Flash-1017 | DS-V4.1-Flash | K3 | GLM-5.3 | GPT-5.6 Sol | Opus 5 |” / complete row containing “| HLE w/o tools | 42.6 (44.0†) | 36.8 (39.1†) | 43.5 | 42.0† | 44.5 | 56.3 |”
材料版本
HF revision 08c8657f02291e11b6f6b63e0e16014f8e748518; 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-1017 · Humanity's Last Exam(V4.1-Flash-1017 comparison table; non-text-only value, metric/set unspecified),DeepSeek-V4.1-Flash-1017 reported comparison配置,Reported score 42.6(具体成绩公布时间未确认)。官方出处 DeepSeek-V4.1-Flash-1017 official Hugging Face model card(主文,HF revision 08c8657f02291e11b6f6b63e0e16014f8e748518; current card snapshot)Official model card / table headed “| Benchmark | DS-V4.1-Flash-1017 | DS-V4.1-Flash | K3 | GLM-5.3 | GPT-5.6 Sol | Opus 5 |” / complete row containing “| HLE w/o tools | 42.6 (44.0†) | 36.8 (39.1†) | 43.5 | 42.0† | 44.5 | 56.3 |”,https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017。Benchlog https://benchlog.lekshome.cc/evidence/deepseek-v41-flash-1017/ev-v41-flash-1017-001/

关联成绩与条件

DeepSeek-V4.1-Flash-1017 · Humanity's Last Exam 成绩与配置
指标与成绩配置与评测条件证据关系
Reported score42.6原文 42.6 · 单位 未标注
公布 未确认
DeepSeek-V4.1-Flash-1017 reported comparison
设置
The table reports this named checkpoint; reasoning_effort and most evaluation settings are not stated in this card.
未知项
Do not copy reasoning_effort=100 from the separate V4.1-Flash card.、Do not merge these scores with DeepSeek-V4.1-Flash.
工具
禁止工具
推理预算
未记录
框架
未记录
协议
未说明
条件
The first value is retained separately from the † text-only subset; the row does not print a metric label.

直接支持该成绩

在排名中查看此成绩