跳转到主要内容

DeepSeek V3 (Dec '24)

DeepSeekDeepSeek开源权重MIT + Model License (Commercial use allowed)

描述

A powerful Mixture-of-Experts (MoE) language model with 671B total parameters (37B activated per token). Features Multi-head Latent Attention (MLA), auxiliary-loss-free load balancing, and multi-token prediction training. Pre-trained on 14.8T tokens with strong performance in reasoning, math, and code tasks.

发布日期
2024-12-26
参数规模
671.0B
上下文长度
—
支持模态
text

能力雷达图

70
general
50
coding
70
reasoning
51
science估算
64
agents
0
multimodal

缺少专门科学评测时,Science 由 LLM Stats 科学得分或推理能力估算。

排行榜排名

暂无排名数据

基准测试分数 (LLM Stats)

(LLM Stats (zeroeval))

Chat

IFEvalGoogle Research (2023)86.1%自报

Factuality

SimpleQA24.9%自报

General

MMLU88.5%自报
C-Eval86.5%自报
Aider-Polyglot Edit79.7%自报
CSimpleQA64.8%自报
Aider-Polyglot49.6%自报

Language

CLUEWSC90.9%自报
MMLU-Redux89.1%自报
MMLU-Pro75.9%自报

Long Context

LongBench v248.7%自报

Math

MATH-50090.2%自报
CNMO 202443.2%自报
AIME 202439.2%自报

Reasoning

DROP91.6%自报
HumanEval-Mul82.6%自报
FRAMES73.3%自报
GPQANYU + Cohere + Anthropic (2023)59.1%自报
SWE-Bench Verified42.0%自报
LiveCodeBench37.6%自报

AA 评测指数

(Artificial Analysis)

暂无 AA 评测数据

LLM Stats 分类评分

(LLM Stats (zeroeval))
Chat
90
Instruction Following
90
Language
80
Legal
80
Finance
80
Healthcare
80
Math
70
Reasoning
70
Search
70
Structured Output
70
General
70
Physics
60
Biology
60
Chemistry
60
Long Context
50
Code
50
Frontend Development
40
Factuality
20

定价

输入价格$0.32 / 1M tokens
输出价格$0.89 / 1M tokens
混合价格(3:1)$0.4625 / 1M tokens

速度

Tokens/秒73.2
首Token延迟0.87s
首回答延迟0.87s

供应商价格排行

供应商价格排行

5 个供应商

最便宜: Alibaba (China)最贵: Helicone
供应商输入输出
1Alibaba (China)最便宜
$0.287
$1.147
2Qiniu
$0.28986
$1.15942
3DeepSeek主要
$0.32
$0.89
4DeepInfra
$0.32
$0.89
5Helicone
$0.56
$1.68

比较该模型在不同 API 供应商之间的定价。

外部链接