Grok 4.5 (high)
SpaceXAIGrokProprietary
Descripción
Grok 4.5 is SpaceXAI's frontier model for coding, agentic tasks, and knowledge work. Trained alongside Cursor across tens of thousands of NVIDIA GB300 GPUs, it uses large-scale reinforcement learning focused on multi-step software engineering and other technical work. The model supports text and image inputs, reasoning, function calling, structured outputs, and a 500K-token context window, and is served at 80 tokens per second.
Fecha de lanzamiento
2026-07-08
Parámetros
—
Longitud del contexto
500K
Modalidades
image, pdf, text
Radar de capacidades
53
general
70
coding
93
reasoning
69
science
60
agents
80
multimodal
Rankings
| Dominio | #Posición | Puntuación | Fuente |
|---|---|---|---|
| Capacidad agéntica | 24 | 58.0 | LS |
| Ranking de codificación | 26 | 91.0 | AA |
| Ranking general | 17 | 88.0 | AA |
| Razonamiento matemático | 16 | 91.0 | LB |
| Razonamiento | 16 | 87.0 | LB |
| Ciencia | 23 | 88.0 | AA |
Puntuaciones de benchmarks (LLM Stats)
(LLM Stats (zeroeval))Agents
AutomationBench-AA
51.4%
Tau3 Banking
33.0%
Code
DeepSWE 1.0
62.0%Aut.
DeepSWE 1.1
54.0%
DeepSWE
53.0%Aut.
SWE-Marathon
29.0%Aut.
General
Artificial Analysis
54.0%
Knowledge
AA-Omniscience Index
126.00 / 200
OmniScience (non-hallucination rate)
46.0%
Reasoning
GPQANYU + Cohere + Anthropic (2023)
93.0%
Terminal-Bench 2.1
83.3%Aut.
SWE-Bench ProPrinceton NLP (2024)
64.7%Aut.
FrontierCode 1.1
42.4%
Science
OmniScience
52.0%
Índices de evaluación AA
(Artificial Analysis)Coding Index(Artificial Analysis)72.4
Intelligence Index(Artificial Analysis)55.8
Gpqa(NYU + Cohere + Anthropic (2023))0.9
Terminalbench V2 10.8
Lcr(Artificial Analysis)0.7
Scicode(UIUC + Argonne National Lab (2024))0.5
Hle(Center for AI Safety + Scale AI (2025))0.4
Tau Banking0.4
Puntuaciones por categoría LLM Stats
(LLM Stats (zeroeval))Physics90
Biology90
Chemistry90
Reasoning60
General60
Tool Calling60
Science50
Knowledge50
Agents50
Code50
Precios
Precio de entrada$2 / 1M tokens
Precio de salida$6 / 1M tokens
Precio mixto (3:1)$3 / 1M tokens
Precio de lectura caché$0.3 / 1M tokens
Velocidad
Tokens/seg56.8
Retraso del primer token11.57s
Tiempo hasta la respuesta11.57s
Ranking de Precios por Proveedor
Ranking de Precios por Proveedor
18 proveedores
Más barato: xAIMás caro: Venice AI
ProveedorEntradaSalida
1xAIMás barato
$0
$0.00001
2Requesty
$1.8
$5.4
3SpaceXAIPRINCIPAL
$2
$6
4NanoGPT
$2
$6
5Abacus
$2
$6
6OpenRouter
$2
$6
7OpenCode Go
$2
$6
8ZenMux
$2
$6
9Kilo Gateway
$2
$6
10GitHub Copilot
$2
$6
11OpenCode Zen
$2
$6
12AIHubMix
$2
$6
13DevPass (LLM Gateway)
$2
$6
14CrossModel
$2
$6
15Pioneer
$2
$6
16DaoXE
$2
$6
17Ofox
$2
$6
18Venice AI
$2.27
$6.8
Comparar precios entre diferentes proveedores de API para este modelo.