Deepseek R1

Deepseek R1
DeepSeek-R1 是基於 DeepSeek-V3(總計參數量為 6710 億,每代參量為 370 億)構建的第一代推理模型。它結合了大規模強化學習(RL),以增強其思維鏈和推理能力,在數學、代碼以及多步推理任務中表現出色。
Intelligence(Medium)
Speed(Slow)
Input Supported Modalities
No
Is Reasoning Model
128,000
Context Window
131,072
Maximum Output Tokens
-
Knowledge Cutoff
Pricing
¥3.96 /M tokens
Input
¥15.77 /M tokens
Output
¥6.91 /M tokens
Blended Price
Quick Simple Comparison
DeepSeek R1 Distill Llama 8B
DeepSeek-V2-Chat
DeepSeek-Coder-V2
Basic Parameters
GPT-4.1 Technical Parameters
Parameter Count
671,000.0M
Context Length
128.00k tokens
Training Data Cutoff
Open Source Category
Open Weights (Permissive License)
Multimodal Support
Text Only
Throughput
9
Release Date
2025-01-20
Response Speed
24.38,148 tokens/s
Benchmark Scores
Below is the performance of claude-monet in various standard benchmark tests. These tests evaluate the model's capabilities in different tasks and domains.
Intelligence Index
6022
Large Language Model Intelligence Level
Coding Index
4870
Indicator of AI model performance on coding tasks
Math Index
-
Capability indicator in solving mathematical problems, mathematical reasoning, or performing math-related tasks
MMLU Pro
84.4
Massive Multitask Multimodal Understanding - Testing understanding of text, images, audio, and video
GPQA
70.8
Graduate Physics Questions Assessment - Testing advanced physics knowledge with diamond science-level questions
HLE
9.3
The model's comprehensive average score on the Hugging Face Open LLM Leaderboard
LiveCodeBench
61.7
Specific evaluation focused on assessing large language models' ability in real-world code writing and solving programming competition problems
SciCode
35.7
The model's capability in code generation for scientific computing or specific scientific domains
HumanEval
97.7
Score achieved by the AI model on the specific HumanEval benchmark test set
Math 500 Score
96.6
Score on the first 500 larger, more well-known mathematical benchmark tests
AIME Score
68.3
An indicator measuring an AI model's ability to solve high-difficulty mathematical competition problems (specifically AIME level)
Featured Recommended AI Models
Gemini 2.0 Flash Lite (Preview)
google

¥0.58
Input tokens/million
¥2.16
Output tokens/million
1M
Context Length
Gemini 1.0 Pro
google

¥3.6
Input tokens/million
¥10.8
Output tokens/million
33k
Context Length
GPT 4
openai

¥216
Input tokens/million
¥432
Output tokens/million
8192
Context Length
Claude 3 Opus
anthropic

¥108
Input tokens/million
¥540
Output tokens/million
200k
Context Length
Deepseek R1
deepseek

¥3.96
Input tokens/million
¥15.77
Output tokens/million
128k
Context Length
Gemma 3 4B Instruct
google

-
Input tokens/million
-
Output tokens/million
128k
Context Length
Gemini 1.5 Pro (May '24)
google

¥18
Input tokens/million
¥72
Output tokens/million
2M
Context Length
Llama 3.2 Instruct 11B (Vision)
meta

¥0.43
Input tokens/million
¥0.43
Output tokens/million
128k
Context Length