llmboard.ai
Benchmarks
CompareRankings
llmboard.ai
Benchmarks
CompareRankings
HomeModelsDeepSeek-V4-Pro

DeepSeek model product

DeepSeek-V4-Pro

Open MoE flagship with million-token context for coding and long agent runs

Updated Aug 10, 2026. Default version: DeepSeek V4 Pro

Compare
LLMBoard score80.1DeepSeek-V4-Pro-Max
Coverage100%11 benchmark families
Context window1MTokens
Official input priceN/AOfficial price unavailable

On this page

  • Specification
  • Capability
  • Benchmarks
  • Arena
  • Pricing
  • Versions
  • About
  • Compare
  • Similar models
  • FAQ

Model specification

Structured fields from the published default version.

Version
DeepSeek V4 Pro
Released
Apr 24, 2026
Knowledge cutoff
May 1, 2025
Parameters
N/A
Context window
1M
Max output
384K
Inputs
text
Outputs
text
Open weights
Yes
License
Unspecified

Capability profile

This profile uses the latest version under this unique model that has a calculated LLMBoard score. Arena and price are excluded.

DeepSeek-V4-Pro-Max category scores

Benchmark results

Published benchmark records for the scored version DeepSeek-V4-Pro-Max.

22 rows
Columns

Show columns

CorpusQA 1M0.612100.0%CAug 7, 2026
CSimpleQA0.817100.0%CAug 7, 2026
LiveCodeBench0.9173100.0%CAug 7, 2026
MathArena Apex0.917100.0%CAug 7, 2026
MRCR 1M0.813100.0%CAug 7, 2026
CodeForces1.021693.3%CAug 7, 2026
HMMT Feb 261.021190.0%CAug 7, 2026
IMO-AnswerBench0.951977.8%CAug 7, 2026
MMLU-Pro0.9612996.1%CAug 7, 2026
SWE-bench Multilingual0.883478.8%CAug 7, 2026
SWE-Bench Verified0.8810493.2%CAug 7, 2026
SimpleQA0.694682.2%CAug 7, 2026
FrontierSWE0.3121521.4%BAug 7, 2026
Toolathlon0.5123163.3%CAug 7, 2026
FrontierCode 1.10.2131514.3%BAug 7, 2026
Terminal-Bench 2.00.7144972.9%CAug 7, 2026
MCP Atlas0.7153051.7%CAug 7, 2026
BrowseComp0.8175871.9%CAug 7, 2026
LiveBench0.7203848.6%BAug 7, 2026
Humanity's Last Exam0.5239275.8%CAug 7, 2026
GPQA0.92423390.1%CAug 7, 2026
SWE-Bench Pro0.6304432.6%CAug 7, 2026

Arena results

Preference and agent-evaluation signals from published Arena datasets.

96 rows
Columns

Show columns

text factualityjapanese101460.2441N/AAug 6, 2026
text factualitykorean101423.0483N/AAug 6, 2026
text factualitygerman111440.8397N/AAug 6, 2026
text factualityspanish191454.61,194N/AAug 6, 2026
text style controljapanese201461.9608N/AAug 6, 2026
textjapanese221449.8608N/AAug 6, 2026
text style controlgerman231471.4882N/AAug 6, 2026
agent steerabilityoverall240.0N/A32.4KAug 6, 2026
agentoverall26-0.0N/A1.3MAug 6, 2026
agent bash recovery stepsoverall260.0N/A44.6KAug 6, 2026
textgerman271460.4882N/AAug 6, 2026
textpolish271459.81,007N/AAug 6, 2026
text factualityfrench271483.41,538N/AAug 6, 2026
text factualityindustry medicine and healthcare271489.62,836N/AAug 6, 2026
textcreative writing281445.48,475N/AAug 6, 2026
agent praise complaintoverall29-0.0N/A7.6KAug 6, 2026
text factualitycreative writing291446.07,471N/AAug 6, 2026
text factualitymulti turn291476.08,019N/AAug 6, 2026
textmulti turn301466.59,251N/AAug 6, 2026
agent tool hallucinationoverall320.0N/A1.2MAug 6, 2026
agent task outcome explicitoverall33-0.0N/A19.6KAug 6, 2026
textindustry medicine and healthcare341464.13,521N/AAug 6, 2026
textindustry writing and literature and language341447.112,369N/AAug 6, 2026
text factualityindustry entertainment and sports and media341437.310,478N/AAug 6, 2026
text factualityindustry life and physical and social science341482.17,134N/AAug 6, 2026
text factualityindustry writing and literature and language341449.311,754N/AAug 6, 2026
textenglish351457.522,730N/AAug 6, 2026
textindustry entertainment and sports and media351430.711,151N/AAug 6, 2026
textindustry life and physical and social science351468.38,098N/AAug 6, 2026
text factualityindustry legal and government351475.43,264N/AAug 6, 2026
textindustry legal and government361460.63,980N/AAug 6, 2026
textspanish361455.31,553N/AAug 6, 2026
textindustry business and management and financial operations371443.510,136N/AAug 6, 2026
text factualitychinese371497.42,179N/AAug 6, 2026
text factualitylonger query371473.521,836N/AAug 6, 2026
text style controlindustry writing and literature and language371452.212,369N/AAug 6, 2026
textexclude ties381448.138,848N/AAug 6, 2026
textfrench381468.31,999N/AAug 6, 2026
textoverall391450.051,266N/AAug 6, 2026
texthard prompts english391463.815,953N/AAug 6, 2026
textinstruction following391444.317,416N/AAug 6, 2026
textkorean391412.1981N/AAug 6, 2026
text factualityexpert391485.94,140N/AAug 6, 2026
text factualityinstruction following391455.016,836N/AAug 6, 2026
text style controlcreative writing391446.08,475N/AAug 6, 2026
text style controlpolish391464.11,007N/AAug 6, 2026
textlonger query401457.522,336N/AAug 6, 2026
text factualityindustry business and management and financial operations401458.29,128N/AAug 6, 2026
text factualityindustry mathematical401445.82,222N/AAug 6, 2026
text style controlfrench401481.41,999N/AAug 6, 2026
text style controlmulti turn401474.49,251N/AAug 6, 2026
textrussian411449.35,394N/AAug 6, 2026
text factualitycoding411504.814,678N/AAug 6, 2026
text style controlkorean411421.3981N/AAug 6, 2026
texthard prompts421460.833,976N/AAug 6, 2026
text factualityhard prompts421477.333,934N/AAug 6, 2026
text factualityhard prompts english421487.315,390N/AAug 6, 2026
text style controlindustry legal and government421470.43,980N/AAug 6, 2026
webdevwebdev-react421440.68,296N/AAug 6, 2026
textnon english431439.028,536N/AAug 6, 2026
text factualityoverall431453.951,202N/AAug 6, 2026
text factualityexclude ties431456.438,797N/AAug 6, 2026
text factualitynon english431441.228,503N/AAug 6, 2026
text style controlspanish431455.81,553N/AAug 6, 2026
webdevoverall431446.311,908N/AAug 6, 2026
webdevwebdev431446.311,908N/AAug 6, 2026
text style controlinstruction following441452.617,416N/AAug 6, 2026
text style controllonger query441472.322,336N/AAug 6, 2026
text factualityindustry software and it services451487.820,773N/AAug 6, 2026
text style controlindustry entertainment and sports and media451435.311,151N/AAug 6, 2026
text style controlindustry life and physical and social science451480.08,098N/AAug 6, 2026
textindustry software and it services461468.421,041N/AAug 6, 2026
text factualityenglish461463.322,689N/AAug 6, 2026
text factualitymath461441.22,147N/AAug 6, 2026
text style controlindustry medicine and healthcare471476.63,521N/AAug 6, 2026
text style controlindustry business and management and financial operations481459.810,136N/AAug 6, 2026
textexpert491465.04,950N/AAug 6, 2026
text style controlhard prompts491479.833,976N/AAug 6, 2026
text style controlhard prompts english491483.215,953N/AAug 6, 2026
webdevwebdev-html491432.51,263N/AAug 6, 2026
textcoding501469.915,292N/AAug 6, 2026
text style controloverall501457.151,266N/AAug 6, 2026
text style controlexclude ties501460.438,848N/AAug 6, 2026
text style controlrussian501456.85,394N/AAug 6, 2026
textchinese511486.82,670N/AAug 6, 2026
textindustry mathematical511453.82,813N/AAug 6, 2026
text factualityrussian511454.54,439N/AAug 6, 2026
text style controlenglish511465.922,730N/AAug 6, 2026
text style controlnon english511445.228,536N/AAug 6, 2026
text style controlexpert521481.84,950N/AAug 6, 2026
text style controlindustry mathematical521459.92,813N/AAug 6, 2026
text style controlindustry software and it services521491.421,041N/AAug 6, 2026
text style controlchinese531495.62,670N/AAug 6, 2026
text style controlcoding561501.015,292N/AAug 6, 2026
textmath591441.42,732N/AAug 6, 2026
text style controlmath631443.82,732N/AAug 6, 2026

Pricing

Official vendor API PAYG pricing is summarized first. The table then lists individual provider offerings without treating their minimum as the official price.

Official API
N/A
Official provider
N/A
Lowest third-party
N/A
Tracked offerings
0
No published price snapshot

The default version has no provider offering with current input or output token prices.

Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.

DeepSeek-V4-Pro versions

All published versions linked to this unique model. The score columns identify the version used by the current overall ranking.

2 rows
Columns

Show columns

DeepSeek V4 ProApr 24, 2026N/AN/A1M384KYesUnspecified
DeepSeek-V4-Pro-MaxApr 23, 202680.11.6T1M393.2KNoMIT

What is DeepSeek-V4-Pro?

A concise description based on the published model registry.

Open MoE flagship with million-token context for coding and long agent runs

Use the benchmark, Arena and pricing sections above as separate evidence. A missing field means the current data snapshot does not support that claim.

Data snapshot: 2026-08-07. Editorial model content is not available in the backend.

DeepSeek-V4-Pro vs nearby models

Open a comparison with the three ranked models immediately above and below this model.

DeepSeek-V4-ProvsSeed 2.1 TurboDeepSeek-V4-ProvsGLM 5.2DeepSeek-V4-ProvsHy3DeepSeek-V4-ProvsClaude Opus 4.7DeepSeek-V4-ProvsGemini 2.5 ProDeepSeek-V4-ProvsGPT-5.6-Luna

Models similar to DeepSeek-V4-Pro

Recommendations prioritize the same model type and family, then the closest published LLMBoard score.

#18-4.6
DE

DeepSeek-V3.2

DeepSeek

75.5 LLMBoard

DetailsCompare
#28-8.4
DE

DeepSeek-V4-Flash

DeepSeek

71.7 LLMBoard

DetailsCompare
#32-10.6
DE

DeepSeek-V2.5

DeepSeek

69.5 LLMBoard

DetailsCompare
#101-36.0
DE

DeepSeek-R1

DeepSeek

44.1 LLMBoard

DetailsCompare
#119-42.0
DE

DeepSeek-V3

DeepSeek

38.1 LLMBoard

DetailsCompare
#126-44.1
DE

DeepSeek-V3.1

DeepSeek

36.0 LLMBoard

DetailsCompare

FAQ

Common questions about DeepSeek-V4-Pro.

When was DeepSeek-V4-Pro released?

DeepSeek-V4-Pro's default version was released on Apr 24, 2026.

How much does DeepSeek-V4-Pro cost?

No official standard PAYG price is currently available for DeepSeek-V4-Pro.

Who created DeepSeek-V4-Pro?

DeepSeek-V4-Pro is published under DeepSeek in the model registry.

What is the context window for DeepSeek-V4-Pro?

The default version has a 1M token context window.

Is DeepSeek-V4-Pro open weight?

Yes. The default version is marked as open weight under an unspecified license.

How many API providers offer DeepSeek-V4-Pro?

No published provider offering is currently linked to the default version.

What models should I compare DeepSeek-V4-Pro with?

Nearby ranked alternatives include Seed 2.1 Turbo, GLM 5.2, Hy3.

Rankings

OverallCodingText ArenaPricing

Modalities

Image GenerationVideo GenerationSpeech-to-TextEmbeddings

Benchmarks

All BenchmarksReasoningMathCoding

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai