Deepseek V 3 0324
DeepSeek-V3-0324, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token, an improved iteration over DeepSeek-V3.
Input
Output
Context
131K
Max Output
8K
Parameters
671B
Technical Specifications
Model TypeChat
Context Window131K
Max Output Tokens8K
Parameters671B
Training Cutoff—
Licensemit
Capabilities
Input Modalities
text
Output Modalities
text
Features
code_generationfunction_callingjson_modereasoningstreamingtext_generation
Benchmarks
Chatbot Arena
#29
Rank (Text)
+4/-4
arena text ci 95
1376
Arena Score (Text)
27,391
Votes (Text)
Artificial Analysis
5.2%
HLE
52.0%
AIME
65.5%
GPQA
35.8%
SciCode
94.2%
MATH 500
81.9%
MMLU Pro
41.0
Math
22.0
Coding
40.5%
LiveCodeBench
22.3
Intelligence
Resources & Links
Related Tools
Data sourced from official provider APIs and documentation
Last updated: May 5, 2026
Start building with the right model.
From model selection to production, one platform, no fragmentation.