所有发布••

Open weights release

•

Released 2026年4月

DeepSeek V4 Flash 0420:本次发布的智能、性能与价格

模型摘要

智能

24
Artificial Analysis Intelligence Index
智能为 4 档中的第 3 档。
无
每秒输出 token 数
速度在 4 档中的档位未知。

成本

输入 US$0.112输出 US$0.234缓存折扣 79%
$0.10
Intelligence Index 每项任务的成本
成本为 4 档中的第 2 档。

冗长度

130M
Intelligence Index 输出 token 数
冗长度为 4 档中的第 2 档。

DeepSeek V4 Flash 0420 发布包含 3 个模型,各自具有不同的智能、性能与价格特征。下方对这 3 个模型的关键指标进行了比较。

  • 智能方面,DeepSeek V4 Flash 0420 中得分最高的模型是 DeepSeek V4 Flash 0420 (High)(24)。
  • 输出速度方面,最快的模型是 DeepSeek V4 Flash 0420 (Max)(59 token/秒)。
  • 延迟方面,DeepSeek V4 Flash 0420 (Max)(97.01 秒) 的首个答案 token 等待时间最短。
  • 价格方面,DeepSeek V4 Flash 0420 (Max)($0.09) 的单任务成本最低。不同模型的价格差异最高可达 1.1 倍。

Artificial Analysis Intelligence Index · Higher is better
Output tokens per second · Higher is better
Weighted average cost (USD) per Intelligence Index task · Lower is better

智能

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.3.2 incorporates 10 evaluations: AA-Briefcase v1.1, GDPval-AA v2.1, AutomationBench-AA, Terminal-Bench 4.0, SciCode, Humanity's Last Exam, GDP.pdf, CritPt, AA-Omniscience, AA-LCR v1.1
Estimate (independent evaluation forthcoming)

Intelligence Index 与每项任务的成本

Artificial Analysis Intelligence Index · Weighted average cost (USD) per Artificial Analysis Intelligence Index task
Most attractive quadrant
DeepSeek V4 Flash 0420
Pareto line

成本

每项 Intelligence Index 任务的成本

Weighted average cost (USD) per Intelligence Index task · Segmented by token type · Lower is better

速度与延迟

输出速度

Output tokens per second · Higher is better

能力得分

能力指数

衡量模型在特定能力与行业中的表现
Finance & Accounting Index

Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, Humanity's Last Exam, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better

Strategy & Ops Index

Incorporates 6 evaluations: GDPval-AA v2.1, AA-Briefcase v1.1, AA-Omniscience, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better

Legal Index

Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, Humanity's Last Exam, AA-LCR v1.1, GDP.pdf, AutomationBench-AA · Higher is better

Healthcare & Medical Index

Incorporates 6 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, MLCR-AA, Humanity's Last Exam, AutomationBench-AA · Higher is better

Engineering Index

Incorporates 6 evaluations: AA-Omniscience, Humanity's Last Exam, CritPt, GDPval-AA v2.1, AA-Briefcase v1.1, Terminal-Bench 4.0 · Higher is better

Economics Index

Incorporates 5 evaluations: AA-Omniscience, Humanity's Last Exam, GDPval-AA v2.1, AA-Briefcase v1.1, AA-LCR v1.1 · Higher is better

Evaluations

Intelligence evaluations measured independently by Artificial Analysis · Higher is better
查看更多

Agentic knowledge work, Elo

Agentic SaaS workflows

Agentic real-world work tasks, Elo

Reasoning & knowledge

Professional document reasoning, All-pass

Agentic coding & terminal use

Long context reasoning

SciCodeUnder review

Coding

Physics reasoning

Quantitative analysis on spreadsheets & documents

Agentic business operations

Kubernetes incident root-cause analysis

DeepSeek 的更多发布

更多详情

权重
服务商基准测试
DeepSeek V4 Flash 0420 (High)
DeepSeek 标志DeepSeek
24
284B
推理时启用 13B 个参数
1M
US$0.1
-
DeepInfraGMIParasailSiliconFlow
DeepSeek V4 Flash 0420 (Max)
DeepSeek 标志DeepSeek
24
284B
推理时启用 13B 个参数
1M
US$0.1
59
GMIDeepInfraSiliconFlowParasail
DeepSeek V4 Flash 0420 (Non-reasoning)
DeepSeek 标志DeepSeek
19
284B
推理时启用 13B 个参数
1M
US$0.1
-
GMI