DeepSeek V3 0324
DeepSeekDeepSeekOpen WeightMIT + Model License (Commercial use allowed)
Description
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.
Release Date
2025-03-25
Parameters
671.0B
Context Length
164K
Modalities
text
Capability Radar
31
general
30
coding
54
reasoning
44
science
47
agents
0
multimodal
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Code Ranking | 406 | 33.0 | AA |
| General Ranking | 333 | 41.0 | AA |
| Science | 363 | 41.0 | AA |
Benchmark Scores (LLM Stats)
(LLM Stats (zeroeval))Language
MMLU-Pro
81.2%SR
Math
MATH-500
94.0%SR
AIME 2024
59.4%SR
Reasoning
GPQANYU + Cohere + Anthropic (2023)
68.4%SR
LiveCodeBench
49.2%SR
AA Evaluation Indices
(Artificial Analysis)Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))94.2
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))81.9
Gpqa(NYU + Cohere + Anthropic (2023))65.5
Aime(MAA (Mathematical Association of America))52.0
Tau2(Sierra + U Toronto + Vector Institute (2025))47.1
Ifbench(Google Research (2023))41.0
Math Index(Artificial Analysis)41.0
Aime 25(MAA (Mathematical Association of America))41.0
Lcr(Artificial Analysis)40.7
Livecodebench(UC Berkeley + MIT + Cornell (2024))40.5
Scicode(UIUC + Argonne National Lab (2024))39.0
Coding Index(Artificial Analysis)21.2
Terminalbench Hard(Stanford × Laude Institute (2026))15.2
Terminalbench V2 113.9
Intelligence Index(Artificial Analysis)9.7
Tau Banking4.7
Hle(Center for AI Safety + Scale AI (2025))4.7
Terminalbench V4 00.0
LLM Stats Category Scores
(LLM Stats (zeroeval))Language80
Legal80
Math80
Finance80
Healthcare80
Physics70
Reasoning70
General70
Biology70
Chemistry70
Code50
Pricing
Input Price$0.24 / 1M tokens
Output Price$0.9 / 1M tokens
Blended Price (3:1)$0.405 / 1M tokens
Cache Read Price$0.11 / 1M tokens
Speed
Tokens/sec0.0
Time to First Token0.00s
Time to Answer0.00s
Provider Price Ranking
Provider Price Ranking
5 providers
Cheapest: DeepInfraMost Expensive: Kilo Gateway
ProviderInputOutput
1DeepInfraCheapest
$0
$0
2NanoGPT
$0.2
$0.77
3DeepSeekPRIMARY
$0.24
$0.9
4OpenRouter
$0.29
$1.14
5Kilo Gateway
$0.29
$1.14
Compare pricing across different API providers for this model.