DeepSeek V3.2 is DeepSeek's V3-generation model upgrade underlying both the deepseek-chat (non-thinking) and deepseek-reasoner (thinking) modes, improving efficiency and reasoning quality over V3.1. It is designed as a strong, low-cost general-purpose and reasoning model.
数学#99写作、文学与语言#112生命科学、自然科学与社会科学#115娱乐、体育与媒体#125
概览
费用比率
0.1x
上下文
164K
输入
输出
推理
工具调用
结构化输出
定价/M tokens
输入$0.26
缓存输入$0.13
输出$0.38
上下文
上下文长度163,840
最大输出令牌147,456
知识截止日期-
性能
吞吐量35 tok/s
延迟3.25s
Llama 4 Maverick is Meta's high-capability open-weight Mixture-of-Experts model, offering strong multimodal (text and image) understanding, reasoning, and coding at efficient inference cost. It targets general-purpose assistant and agentic use cases needing frontier-adjacent quality in an open model.
图像理解#123医学与医疗保健#245法律与政府#247写作、文学与语言#249
概览
费用比率
0.2x
上下文
524K
输入
输出
推理
工具调用
结构化输出
定价/M tokens
输入$0.35
缓存输入$0.17
输出$1.00
上下文
上下文长度524,288
最大输出令牌32,768
知识截止日期2024-08-31
性能
吞吐量147 tok/s
延迟1.19s
基准测试
推理、编程和智能体任务的正面对比得分,以及各领域排名。
智能
64.6
Claude Fable 5.2 (Max, Default Fallback)
62.1
GPT-6.2 Astra (Max)
61.4
Gemini 4 Neon (Xhigh)
60.0
Gemini 4 Carbon (High)
59.1
Claude Opus 5.5 (Max, Default Fallback)
57.3
GPT-6.2 Sol (Max)
DeepSeek V3.2 暂无数据
Llama 4 Maverick 暂无数据
编程
1824
Claude Fable 5.2 (xHigh)
1819
Claude Opus 5.5 (Max)
1772
Claude Sonnet 5.5 (xHigh)
1769
Gemini 4 Carbon (High)
1766
GPT-6.2 Astra (Max)
1362
DeepSeek V3.2
Llama 4 Maverick 暂无数据
来源:Code Arena
自动化与工具使用
0.27
Claude Fable 5.2 (Max)
0.19
Claude Opus 5.5 (Max)
0.18
Gemini 4 Neon (High)
0.16
Gemini 4 Carbon (High)
0.16
Claude Sonnet 5.5 (Max)
0.15
GPT-6.2 Astra (Max)
DeepSeek V3.2 暂无数据
Llama 4 Maverick 暂无数据
来源:Agent Arena
软件与信息技术服务
arena.ai1549
Gemini 4 Carbon (High)
1547
Gemini 4 Argon (High)
1546
Muse Wonder (Max)
1541
Gemini 4 Neon (High)
1540
Claude Opus 4.7 (High)
1538
Claude Fable 5 (High)
1537
Claude Opus 4.6 (High)
1534
Claude Opus 5.5 (High)
1464
DeepSeek V3.2
1358
Llama 4 Maverick
热门比较
Claude Sonnet 5.5 vs GPT-6.1 Terra
Gemini 4 Neon vs GPT-6.2 Sol
GPT-6.2 Sol vs Grok 4.7
Claude Opus 5.5 vs Kimi K3.1 Pro
Kimi K3.1 Pro vs Qwen4 Max
Claude Haiku 5.5 vs GPT-6 Luna
DeepSeek V4 Pro 0813 vs GPT-6.2 Sol
Claude Opus 5.5 vs Mistral Large 4
Kimi K3.1 Pro vs GPT-6.2 Astra
Claude Haiku 5.5 vs DeepSeek V4.1 Flash
Gemini 4 Hydrogen vs GPT-6 Luna
Claude Opus 5.5 vs GPT-6.2 Sol
Claude Fable 5.2 vs Gemini 4 Carbon
DeepSeek V4.1 Flash vs GPT-6 Luna
Claude Fable 5.2 vs GPT-6.2 Astra
GPT-6 Luna vs GPT-6.1 Terra
Claude Opus 5.5 vs Claude Sonnet 5.5
Claude Opus 5.5 vs Gemini 4 Carbon
Claude Opus 5.5 vs GPT-6.1 Terra
GPT-6 Luna vs GLM 5.3 Flash