HomeDeepSeek-R1
671B
Model parameter quantity
DeepSeek
Affiliated organization
Open Source
License Type
January 20, 2025
Release time
Related figures
Model Introduction
DeepSeek-R1 is a model trained through large-scale Reinforcement Learning (RL) without using Supervised Fine-Tuning (SFT) as an initial step. Its performance in mathematics, coding, and reasoning tasks is comparable to that of OpenAI-o1.
Comprehensive score
Language dialogue
Knowledge reserve
Reasoning association
Mathematical calculation
Code writing
Command following
Swipe left and right to view more
Language comprehension ability
Capable of understanding complex contexts and generating logically coherent sentences, though occasionally off in tone control.
7.8
Knowledge coverage scope
Possesses core knowledge of mainstream disciplines, but has limited coverage of cutting-edge interdisciplinary fields.
8.9
Reasoning ability
Capable of building multi-level logical frameworks, achieving over 99% accuracy in complex mathematical modeling.
9.1
Model comparison
DeepSeek-R1 vs Qwen2.5-7B-Instruct
Like Qwen2, the Qwen2.5 language models support up to 128K tokens and can generate up to 8K tokens. They also maintain multilingual support for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more.
DeepSeek-R1 vs Hunyuan-T1-20250822
The deep reasoning model independently developed by Tencent adopts the version number hunyuan-t1-20250822.
DeepSeek-R1 vs Spark-X1
The inference model Spark X1 released by iFlytek, on the basis of leading domestic mathematical tasks, benchmarks the performance of general tasks such as inference, text generation, and language understanding against OpenAI o1 and DeepSeek R1.
Related model
DeepSeek-V3.2
The latest version of Deepseek V3 series models.
DeepSeek-V3.2-Exp
The latest experimental version of Deepseek V3 series models.
DeepSeek-R1-0528
The latest version of Deepseek R1.
DeepSeek-V3-0324
DeepSeek-V3 outperforms other open-source models such as Qwen2.5-72B and Llama-3.1-405B in multiple evaluations and matches the performance of top-tier closed-source models like GPT-4 and Claude-3.5-Sonnet.
DeepSeek-R1-0528
The latest version of Deepseek R1.
Relevant documents
Suno Lead Investor: Deleting Posts Won't Plug Copyright Lawsuit Hole
The much-anticipated AI music generation platform Suno is facing a tough copyright battle, and a candid remark from its lead investor may have handed the opposing side exactly the evidence they were hoping for. C.C. Gong, a partner at Menlo Ventures
Claude Opus 4.7 Launches with Reliability Valued Over Intelligence
Anthropic has maintained an aggressive pace this year, rolling out new features almost every other day. The much-anticipated Claude Opus 4.7 has just been officially released, and interestingly, Anthropic was upfront in the announcement: "This is not
Haier Launches World's Lightest AI Sports Exoskeleton Robot, Weighing Just 1.75 kg
Haier Group has introduced the world's lightest AI-powered exoskeleton robot for sports — the Haier Exoskeleton Robot W3. This launch sets a new industry record for lightness, marking a major breakthrough in lightweight design and intelligent human m
Yaoke Media's First AIGC Drama 'The Mystery of the Bronze in Qinling' Launches Today with AI-Signed Leads
Today marks the official launch of Yaoke Media's AIGC fantasy mystery short drama, "The Secret Story of the Qinling Bronze." Starring the company's first two signed AI actors, Qin Lingyue and Lin Xiyanyan, the story unfolds in the enigmatic Qinling m
Satya Nadella ready to exploit new OpenAI deal
On Wednesday, a Wall Street analyst asked Microsoft CEO Satya Nadella directly how the revised OpenAI partnership would affect the company’s financials.Nadella described the new agreement as a win for everyone. “We feel good about our partnership wit
