DataLearner logoDataLearnerAI
Latest AI Insights
Model Leaderboards
Benchmarks
Model Directory
Model Comparison
Resource Center
Tools
LanguageEnglish
DataLearner logoDataLearner AI

A knowledge platform focused on LLM benchmarking, datasets, and practical instruction with continuously updated capability maps.

Products

  • Leaderboards
  • Model comparison
  • Datasets

Resources

  • Tutorials
  • Editorial
  • Tool directory

Company

  • About
  • Privacy policy
  • Data methodology
  • Contact

© 2026 DataLearner AI. DataLearner curates industry data and case studies so researchers, enterprises, and developers can rely on trustworthy intelligence.

Privacy policyTerms of service
Page navigation
目录
Model catalogDeepSeek-V3.1
DE

DeepSeek-V3.1

聊天大模型

DeepSeek-V3.1

Release date: 2025-08-20更新于: 2025-08-23 01:15:362,369
Live demoGitHubHugging FaceCompare
Parameters
6710.0亿
Context length
128K
Chinese support
Supported
Reasoning ability

DeepSeek-V3.1 is an AI model published by DeepSeek-AI, released on 2025-08-20, for 聊天大模型, with 6710.0B parameters, and 128K tokens context length, requiring about 1340GB storage, under the MIT License license.

Data sourced primarily from official releases (GitHub, Hugging Face, papers), then benchmark leaderboards, then third-party evaluators. Learn about our data methodology

DeepSeek-V3.1

Model basics

Reasoning traces
Supported
Thinking modes
Thinking modes not supported
Context length
128K tokens
Max output length
8192 tokens
Model type
聊天大模型
Release date
2025-08-20
Model file size
1340GB
MoE architecture
Yes
Total params / Active params
6710.0B / 370B
Knowledge cutoff
No data
DeepSeek-V3.1

Open source & experience

Code license
MIT License
Weights license
MIT License- 免费商用授权
GitHub repo
GitHub link unavailable
Hugging Face
https://huggingface.co/deepseek-ai/DeepSeek-V3.1-Base
Live demo
https://chat.deepseek.com/
DeepSeek-V3.1

Official resources

Paper
DeepSeek-V3.1 Release
DataLearnerAI blog
DeepSeek V4没有等到,但是DeepSeekAI把DeepSeek V3升级到DeepSeek V3.1了,小幅更新,但核心架构和参数不变
DeepSeek-V3.1

API details

API speed
3/5
💡Default unit: $/1M tokens. If vendors use other units, follow their published pricing.
Standard pricingStandard
ModalityInputOutput
Text$0.56$1.68
DeepSeek-V3.1

Benchmark Results

DeepSeek-V3.1 currently shows benchmark results led by MMLU (1 / 65, score 93.40), SimpleQA (4 / 45, score 93.40), AIME 2024 (7 / 62, score 93.10). This page also consolidates core specs, context limits, and API pricing so you can evaluate the model from benchmark results and deployment constraints together.

Thinking
All modesNormalThinking
Thinking mode details (1)
All thinking modesDefault (Thinking Mode)
Tool usage
All modesWith toolsNo tools

综合评估

4 evaluations
Benchmark / mode
Score
Rank/total
MMLU
Thinking Mode
93.40
1 / 65
MMLU Pro
Thinking Mode
85
19 / 118
GPQA Diamond
Thinking Mode
80.10
67 / 168
HLE
Thinking Mode
15.90
97 / 134

常识问答

1 evaluations
Benchmark / mode
Score
Rank/total
SimpleQA
Thinking Mode
93.40
4 / 45

编程与软件工程

1 evaluations
Benchmark / mode
Score
Rank/total
LiveCodeBench
Thinking Mode
74.80
34 / 112

数学推理

2 evaluations
Benchmark / mode
Score
Rank/total
AIME 2024
Thinking Mode
93.10
7 / 62
AIME2025
Thinking Mode
88.40
42 / 106

Agent能力评测

1 evaluations
Benchmark / mode
Score
Rank/total
Aider-Polyglot
Thinking Mode
76.30
5 / 26
View benchmark analysisCompare with other models
DeepSeek-V3.1

Publisher

DeepSeek-AI
DeepSeek-AI
View publisher details
DeepSeek-V3.1

Model Overview

DeepSeek V3.1 是 DeepSeek V3 的升级版本,于2025年8月19日发布,知识日期截止到2024年8月,比DeepSeek V3-0324版本多一个月(DeepSeek V3-0324的知识为2024年7月)。


2025年8月19日,官方群里发布更新,官网的DeepSeek更新到DeepSeek V3.1版本,但没有公布更多详情。根据官网的消息,DeepSeekV3.1在复杂数学计算、逻辑推理和代码生成方面进行了优化,提高了准确性和推理深度,尤其是在多步推理任务上表现更好。此外,虽然都是128K输入,但V3.1 在长文本理解和信息提取方面更加精准,减少了冗余回答。


关于DeepSeek-V3.1详细介绍参考: https://www.datalearner.com/blog/1051755634545683 

DataLearner 官方微信

欢迎关注 DataLearner 官方微信,获得最新 AI 技术推送

DataLearner 官方微信二维码