llmboard.aiAI model intelligence
Home

Model Rankings

OverallOpen ModelsAgentCodingReasoningMathKnowledgeInstruction FollowingTextVision
Image GenerationImage Editing
Video GenerationImage to VideoVideo Editing
Text to SpeechSpeech to Text
Embeddings

Efficiency

Chat Token PricingImage PricingVideo PricingAudio Pricing
Chat Speed & LatencyProvider Reliability

Benchmarks

GPQAMMLU-ProAIME 2025SWE-Bench VerifiedMMLUHumanity's Last ExamLiveCodeBenchMATHHumanEvalMMMU-Pro
All Benchmarks

Tools

Model DirectoryCompare Models

Scoring & Data

Scoring & Data
393 models668 benchmarks

Leaderboard Center

Overall RankingCodingCore BenchmarksPrice & ValueRuntime Performance

Modalities

All ModelsImage GenerationImage EditingVideo GenerationImage-to-VideoVideo EditingText-to-SpeechSpeech-to-TextEmbeddings

Data & Methods

Scoring MethodAll BenchmarksReasoningMath

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai

Model vendor

DeepSeek

Chinese AI company developing open and frontier language models, including the DeepSeek-V3 and DeepSeek-R1 model families.

Updated Aug 17, 2026. Data as of 2026-08-17

Website
Models11
Versions28
Open defaults3
CountryCN

On this page

  • Models
  • Scores
  • Highlights
  • About
  • FAQ

DeepSeek models

Default-version specifications and scored-version capability values are labeled separately.

11 rows
Columns

Show columns

Sort by
Model
LLMBoard
Coverage
Context
License
Released
ModelDEDeepSeek-V4-ProDeepSeekLLMBoard90.0Coverage40.0%Context1MLicenseClosed weightsReleasedAug 13, 2026
ModelDEDeepSeek-V4-FlashDeepSeekLLMBoard77.4Coverage20.0%Context1MLicenseOpen weightsReleasedJul 31, 2026
ModelDEDeepSeek-V3.2DeepSeekLLMBoard57.5Coverage60.0%Context131.1KLicenseClosed weightsReleasedDec 1, 2025
ModelDEDeepSeek-R1DeepSeekLLMBoard43.5Coverage80.0%Context131.1KLicenseClosed weightsReleasedMay 28, 2025
ModelDEDeepSeek-V3.1DeepSeekLLMBoard39.2Coverage80.0%Context131.1KLicenseOpen weightsReleasedJan 10, 2025
ModelDEDeepSeek-V3DeepSeekLLMBoard25.5Coverage80.0%Context163.8KLicenseOpen weightsReleasedMar 25, 2025
ModelDEDeepSeek-R1-Distill-QwenDeepSeekLLMBoard14.8Coverage60.0%ContextN/ALicenseClosed weightsReleasedJan 20, 2025
ModelDEDeepSeek-V2.5DeepSeekLLMBoard13.8Coverage100.0%Context8.2KLicenseClosed weightsReleasedMay 8, 2024
ModelDEDeepSeek-R1-Distill-LlamaDeepSeekLLMBoard11.6Coverage60.0%ContextN/ALicenseClosed weightsReleasedJan 20, 2025
ModelDEDeepSeek-VL2DeepSeekLLMBoard0.0Coverage0.0%ContextN/ALicenseClosed weightsReleasedDec 13, 2024
ModelDEJanus ProDeepSeekLLMBoardN/ACoverageN/AContextN/ALicenseClosed weightsReleasedN/A

DeepSeek capability scores

Each unique model uses its latest scored version.

DeepSeek LLMBoard scores

DeepSeek Highlights

Leading DeepSeek models by score, price and context window.

Top scoreDeepSeek-V4-Pro90.0 LLMBoardLowest official inputDeepSeek-V4-Flash$0.14 / 1MLargest contextDeepSeek-V4-Flash1M tokens
Open-weight defaults3of 11 models

What is DeepSeek?

Background and model catalog information for DeepSeek.

Chinese AI company developing open and frontier language models, including the DeepSeek-V3 and DeepSeek-R1 model families.

Model ownership is separate from API hosting. One model can be offered by multiple API providers with different prices.

Vendor
DeepSeek
Models
11
Versions
28
Country
CN
Founded
Not available

Catalog data as of 2026-08-17.

FAQ

Common questions about DeepSeek.

What is DeepSeek's highest-ranked model?

DeepSeek-V4-Pro currently has the strongest LLMBoard score from this vendor.

How many DeepSeek models are tracked?

The catalog contains 11 independently selectable DeepSeek models and 28 versions.

Does DeepSeek host every listed model API?

Not necessarily. Vendor identifies the model developer; API providers are tracked separately.

Does DeepSeek publish open-weight models?

3 current default versions are marked as open weight.