跳轉到主要內容

DeepSeek R1 Distill Qwen 1.5B

DeepSeekDeepSeek開源權重MIT · 商用許可

描述

DeepSeek-R1 is the first-generation reasoning model built atop DeepSeek-V3 (671B total parameters, 37B activated per token). It incorporates large-scale reinforcement learning (RL) to enhance its chain-of-thought and reasoning capabilities, delivering strong performance in math, code, and multi-step reasoning tasks.

發布日期
2025-01-20
參數規模
1.8B
上下文長度
支援模態

能力雷達圖

10
general
7
coding
27
reasoning
7
science
21
agents
0
multimodal

排行榜排名

領域#排名分數來源
程式碼能力榜527
5.0
AA
通用能力榜564
9.0
AA
科學能力565
5.0
AA

基準測試分數 (LLM Stats)

(LLM Stats (zeroeval))

Biology

GPQANYU + Cohere + Anthropic (2023)33.8%自報

Code

LiveCodeBench16.9%自報

Math

MATH-50083.9%自報
AIME 202452.7%自報

AA 評測指數

(Artificial Analysis)
Math Index(Artificial Analysis)
22.0
Intelligence Index(Artificial Analysis)
3.3
Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))
0.7
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))
0.3
Aime 25(MAA (Mathematical Association of America))
0.2
Aime(MAA (Mathematical Association of America))
0.2
Ifbench(Google Research (2023))
0.1
Gpqa(NYU + Cohere + Anthropic (2023))
0.1
Livecodebench(UC Berkeley + MIT + Cornell (2024))
0.1
Scicode(UIUC + Argonne National Lab (2024))
0.1
Hle(Center for AI Safety + Scale AI (2025))
0.0
Lcr(Artificial Analysis)
0.0

LLM Stats 分類評分

(LLM Stats (zeroeval))
Math
70
Reasoning
50
General
50
Physics
30
Biology
30
Chemistry
30
Code
20

定價

輸入價格免費
輸出價格免費
混合價格(3:1)免費

速度

Tokens/秒0.0
首Token延遲0.00s
首回答延遲0.00s

供應商價格排行

暫無提供商資料

外部連結