DeepSeek-V4-Pro-0813 · Humanity's Last Exam(V4-0813/0731 card does not specify metric or task subset) 42.7 · 主文证据(ev-v4-pro-0813-007)

DeepSeek-V4-Pro-0813 的 Humanity's Last Exam · V4-0813/0731 card does not specify metric or task subset 官方出处。DeepSeek-V4-Pro-0813, max reasoning effort · 42.7。见《DeepSeek-V4-Pro-0813 official Hugging Face model card》Official model card / HLE (wo / w tools) row / first value under DeepSeek-V4-Pro-0813。证据 ev-v4-pro-0813-007。

原文与定位

DeepSeek-V4-Pro-0813 · Humanity's Last Exam(V4-0813/0731 card does not specify metric or task subset),DeepSeek-V4-Pro-0813, max reasoning effort配置,Reported score 42.7(具体成绩公布时间未确认)。见《DeepSeek-V4-Pro-0813 official Hugging Face model card》Official model card / HLE (wo / w tools) row / first value under DeepSeek-V4-Pro-0813。 查看成绩条件

| Benchmark | DeepSeek-V4-Pro-0813 | DeepSeek-V4-Flash-0731 | DeepSeek-V4-Pro (Preview) | DeepSeek-V4-Flash (Preview) | GLM-5.2 | Kimi K3 | Opus-4.8 | Fable-5 (w/ fallback) | | HLE (wo / w tools) | 42.7 / 60.0 | 37.8 / 51.5 | 37.7 / 48.2 | 34.8 / 45.1 | 40.5 / 54.7 | 43.5 / 56.0 | 49.8 / 57.9 | 53.3 / 63.0 |
官方材料
DeepSeek-V4-Pro-0813 official Hugging Face model card
定位
主文 · Official model card / HLE (wo / w tools) row / first value under DeepSeek-V4-Pro-0813
材料版本
HF revision 72e1d3230f6c080a530b0a1d46f8eb4602340597; 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-Pro-0813 · Humanity's Last Exam(V4-0813/0731 card does not specify metric or task subset),DeepSeek-V4-Pro-0813, max reasoning effort配置,Reported score 42.7(具体成绩公布时间未确认)。官方出处 DeepSeek-V4-Pro-0813 official Hugging Face model card(主文,HF revision 72e1d3230f6c080a530b0a1d46f8eb4602340597; current card snapshot)Official model card / HLE (wo / w tools) row / first value under DeepSeek-V4-Pro-0813,https://huggingface.co/deepseek-ai/DeepSeek-V4-Pro-0813。Benchlog https://benchlog.lekshome.cc/evidence/deepseek-v4-pro-0813/ev-v4-pro-0813-007/

关联成绩与条件

DeepSeek-V4-Pro-0813 · 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 score42.7原文 42.7 · 单位 未标注
公布 未确认
DeepSeek-V4-Pro-0813, 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
禁止工具
推理预算
未记录
框架
未记录
协议
No-tools column in the source row.
条件
HLE without tools; the original row does not state metric or subset.

直接支持该成绩

在排名中查看此成绩