Grok 3
SpaceXAIGrokProprietary
Descripción
Grok 3, launched by xAI on February 17, 2025, is an advanced AI model with significantly enhanced capabilities compared to Grok 2, boasting an order of magnitude increase in performance. Trained on a vast dataset that includes legal documents among others, and utilizing a massive compute infrastructure with around 200,000 GPUs in a Memphis data center, Grok 3's training used ten times more compute than its predecessor. It features specialized models like Grok 3 Reasoning and Grok 3 Mini Reasoning for complex problem-solving, and it excels in benchmarks like AIME for mathematics and GPQA for PhD-level science.
Fecha de lanzamiento
2025-02-19
Parámetros
—
Longitud del contexto
—
Modalidades
image, text
Radar de capacidades
31
general
43
coding
57
reasoning
49
science
53
agents
80
multimodal
Rankings
| Dominio | #Posición | Puntuación | Fuente |
|---|---|---|---|
| Ranking de codificación | 350 | 43.0 | AA |
| Ranking general | 286 | 44.0 | AA |
| Ranking multimodal | 57 | 56.0 | LS |
| Ciencia | 398 | 37.0 | AA |
Puntuaciones de benchmarks (LLM Stats)
(LLM Stats (zeroeval))Math
AIME 2025
93.3%Aut.
AIME 2024
93.3%Aut.
Multimodal
MMMU
78.0%Aut.
Reasoning
GPQANYU + Cohere + Anthropic (2023)
84.6%Aut.
LiveCodeBench
79.4%Aut.
Índices de evaluación AA
(Artificial Analysis)Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))87.0
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))79.9
Gpqa(NYU + Cohere + Anthropic (2023))69.3
Math Index(Artificial Analysis)58.0
Aime 25(MAA (Mathematical Association of America))58.0
Lcr(Artificial Analysis)58.0
Tau2(Sierra + U Toronto + Vector Institute (2025))48.8
Ifbench(Google Research (2023))46.9
Livecodebench(UC Berkeley + MIT + Cornell (2024))42.5
Aime(MAA (Mathematical Association of America))33.0
Intelligence Index(Artificial Analysis)12.1
Terminalbench Hard(Stanford × Laude Institute (2026))11.4
Hle(Center for AI Safety + Scale AI (2025))4.1
Puntuaciones por categoría LLM Stats
(LLM Stats (zeroeval))Math90
Reasoning90
General90
Multimodal80
Physics80
Healthcare80
Biology80
Chemistry80
Code80
Vision80
Precios
Precio de entrada$4 / 1M tokens
Precio de salida$20 / 1M tokens
Precio mixto (3:1)$8 / 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
3 proveedores
Más barato: xAIMás caro: SpaceXAI
ProveedorEntradaSalida
1xAIMás barato
$0
$0.00002
2Helicone
$3
$15
3SpaceXAIPRINCIPAL
$4
$20
Comparar precios entre diferentes proveedores de API para este modelo.