DeepSeek V3 0324
DeepSeekDeepSeekOpen WeightMIT + Model License (Commercial use allowed)
Descripción
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.
Fecha de lanzamiento
2025-03-25
Parámetros
671.0B
Longitud del contexto
164K
Modalidades
text
Radar de capacidades
34
general
29
coding
54
reasoning
43
science
47
agents
0
multimodal
Rankings
| Dominio | #Posición | Puntuación | Fuente |
|---|---|---|---|
| Ranking de codificación | 326 | 34.0 | AA |
| Ranking general | 289 | 45.0 | AA |
| Ciencia | 314 | 44.0 | AA |
Puntuaciones de benchmarks (LLM Stats)
(LLM Stats (zeroeval))Biology
GPQANYU + Cohere + Anthropic (2023)
68.4%Aut.
Code
LiveCodeBench
49.2%Aut.
Finance
MMLU-Pro
81.2%Aut.
Math
MATH-500
94.0%Aut.
AIME 2024
59.4%Aut.
Índices de evaluación AA
(Artificial Analysis)Math Index(Artificial Analysis)41.0
Coding Index(Artificial Analysis)21.2
Intelligence Index(Artificial Analysis)15.2
Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))0.9
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))0.8
Gpqa(NYU + Cohere + Anthropic (2023))0.7
Aime(MAA (Mathematical Association of America))0.5
Tau2(Sierra + U Toronto + Vector Institute (2025))0.5
Lcr(Artificial Analysis)0.4
Ifbench(Google Research (2023))0.4
Aime 25(MAA (Mathematical Association of America))0.4
Livecodebench(UC Berkeley + MIT + Cornell (2024))0.4
Scicode(UIUC + Argonne National Lab (2024))0.4
Terminalbench Hard(Stanford × Laude Institute (2026))0.2
Terminalbench V2 10.1
Tau Banking0.0
Hle(Center for AI Safety + Scale AI (2025))0.0
Puntuaciones por categoría LLM Stats
(LLM Stats (zeroeval))Legal80
Math80
Language80
Finance80
Healthcare80
Physics70
Reasoning70
General70
Biology70
Chemistry70
Code50
Precios
Precio de entrada$0.27 / 1M tokens
Precio de salida$1.12 / 1M tokens
Precio mixto (3:1)$0.483 / 1M tokens
Precio de lectura caché$0.135 / 1M tokens
Velocidad
Tokens/seg0.0
Retraso del primer token0.00s
Tiempo hasta la respuesta0.00s
Ranking de Precios por Proveedor
Ranking de Precios por Proveedor
4 proveedores
Más barato: NanoGPTMás caro: Kilo Gateway
ProveedorEntradaSalida
1NanoGPTMás barato
$0.2
$0.77
2DeepSeekPRINCIPAL
$0.27
$1.12
3OpenRouter
$0.27
$1.12
4Kilo Gateway
$0.27
$1.12
Comparar precios entre diferentes proveedores de API para este modelo.