Home/Models/DeepSeek V3.1
DeepSeek logo

DeepSeek V3.1

by DeepSeek · Released Aug 2025

Open Source
53.4
avg score
Rank #95
Compare
Better than 59% of all models
Context
33K tokens (~16 books)
Input $/1M
$0.15
Output $/1M
$0.75
Type
text
License
Open Source
Benchmarks
5 tested
Data updated today
About

DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...

Tested on 5 benchmarks with 51.1% average. Top scores: Chatbot Arena Elo — Overall (1417.9%), Lech Mazur Writing (85.2%), Fiction.LiveBench (52.8%).

Looking for similar performance at lower cost?
Phi 4 scores 54.2 (101% as good) at $0.07/1M input · 57% cheaper
Capabilities
coding
38.4
#101 globally
reasoning
28.0
#89 globally
knowledge
69.0
#20 globally
Benchmark Scores
Compare All
Tested on 5 benchmarks · Ranked across 4 categories
Score Distribution (all 233 models)
0255075100
▲ You are here
WeirdML

Unusual and adversarial machine learning challenges. Tests robustness of reasoning about edge cases in ML systems.

38.4
SimpleBench

Deceptively simple questions that humans find easy but AI models often get wrong. Tests common sense and reasoning gaps.

28.0
Lech Mazur Writing

Writing quality evaluation by Lech Mazur. Tests prose quality, coherence, and stylistic ability.

85.2
Fiction.LiveBench

LiveBench fiction analysis. Tests literary comprehension and creative text understanding.

52.8
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Links
Documentation
Community
BenchGecko API
deepseek-chat-v3-1
Specifications
  • Typetext
  • Context33K tokens (~16 books)
  • ReleasedAug 2025
  • LicenseOpen Source
  • StatusActive
  • Cost / Message~$0.001
Available On
DeepSeek logoDeepSeek$0.15
Share & Export
Tweet
DeepSeek V3.1 is an open-source text AI model by DeepSeek, released in August 2025. It has an average benchmark score of 53.4. Context window: 33K tokens.