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

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

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

Large Language Model Intelligence Level

6022

Large Language Model Intelligence Level

Coding Index

Indicator of AI model performance on coding tasks

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

Massive Multitask Multimodal Understanding - Testing understanding of text, images, audio, and video

84.4

Massive Multitask Multimodal Understanding - Testing understanding of text, images, audio, and video

GPQA

Graduate Physics Questions Assessment - Testing advanced physics knowledge with diamond science-level questions

70.8

Graduate Physics Questions Assessment - Testing advanced physics knowledge with diamond science-level questions

HLE

The model's comprehensive average score on the Hugging Face Open LLM Leaderboard

9.3

The model's comprehensive average score on the Hugging Face Open LLM Leaderboard

LiveCodeBench

Specific evaluation focused on assessing large language models' ability in real-world code writing and solving programming competition problems

61.7

Specific evaluation focused on assessing large language models' ability in real-world code writing and solving programming competition problems

SciCode

The model's capability in code generation for scientific computing or specific scientific domains

35.7

The model's capability in code generation for scientific computing or specific scientific domains

HumanEval

Score achieved by the AI model on the specific HumanEval benchmark test set

97.7

Score achieved by the AI model on the specific HumanEval benchmark test set

Math 500 Score

Score on the first 500 larger, more well-known mathematical benchmark tests

96.6

Score on the first 500 larger, more well-known mathematical benchmark tests

AIME Score

An indicator measuring an AI model's ability to solve high-difficulty mathematical competition problems (specifically AIME level)

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)

Output tokens/million

Output tokens/million

Output tokens/million

Output tokens/million

Output tokens/million

Output tokens/million

128k

Context Length

Gemini 1.5 Pro (May '24)

Output tokens/million

Context Length

Llama 3.2 Instruct 11B (Vision)