DeepSeek-V2.5 (Dec '24)
DeepSeekDeepSeek開源權重deepseek
描述
DeepSeek-V2.5 is an upgraded version that combines DeepSeek-V2-Chat and DeepSeek-Coder-V2-Instruct, integrating general and coding abilities. It better aligns with human preferences and has been optimized in various aspects, including writing and instruction following.
發布日期
2024-12-10
參數規模
236.0B
上下文長度
164K
支援模態
text
能力雷達圖
28
general
60
coding
63
reasoning
42
science
62
agents
0
multimodal
排行榜排名
基準測試分數 (LLM Stats)
(LLM Stats (zeroeval))Chat
MT-Bench
0.90 / 100自報
General
MMLU
80.4%自報
AlignBench
80.4%自報
DS-FIM-Eval
78.3%自報
Arena Hard
76.2%自報
AlpacaEval 2.0
50.5%自報
Math
GSM8k
95.1%自報
MATH
74.7%自報
Reasoning
HumanEvalOpenAI (2021)
89.0%自報
BBH
84.3%自報
HumanEval-Mul
73.8%自報
Aider
72.2%自報
DS-Arena-Code
63.1%自報
LiveCodeBench(01-09)
41.8%自報
SWE-Bench Verified
16.8%自報
AA 評測指數
(Artificial Analysis)Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))76.3
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))66.6
Gpqa(NYU + Cohere + Anthropic (2023))42.3
Intelligence Index(Artificial Analysis)6.6
LLM Stats 分類評分
(LLM Stats (zeroeval))Roleplay90
Communication90
Chat80
Language80
Legal80
Math80
Finance80
Healthcare80
Reasoning70
General70
Creativity70
Writing70
Code60
Frontend Development20
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