G
Grok 3
Last updated: Recently
Model Type
Text
Max Context
131K
Max Output
-
Parameter Scale
-
Grok 3 is the latest model from xAI. 131,072 token context window. Includes independent benchmarks from Artificial Analysis.
Input Modality
text
Output Modality
text
Inference Speed
31.028 tokens/s
Latest Release Date
2/19/2025
SDK Ecosystem
-
artificial-analysismanufactureraa-bootstrap
Model Overview Fields
name
Grok 3
Release date
2/19/2025
Performance
31.028 tokens/s
model_creator.name
xAI
AA Evaluation Scores
AA Intelligence Index
25.2
AA Coding Index
19.8
AA Math Index
58
MMLU Pro
0.799
GPQA
0.693
HLE
0.051
LiveCodeBench
0.425
SciCode
0.368
Math-500
0.87
AIME
0.33
AIME 2025
0.58
IFBench
0.469387755102041
LCR
0.546666666666667
TerminalBench Hard
0.113636363636364
TAU2
0.488304093567252
Output Speed (tokens/s)
31.028 tok/s
TTFT (s)
0.683s
First Answer Token (s)
0.683s

