EBEasy BenchmarksLLM model index
Workspace
Overview
Benchmarks
Benchmarks list
Overall Index
Coding
Math
MMLU-Pro
Speed
Value
Models
All models
GPT-5.5 (xhigh)
GPT-5.5 (high)
Claude Opus 4.7 (Adaptive Reasoning, Max Effort)
Gemini 3.1 Pro Preview
GPT-5.4 (xhigh)
Artificial Analysis data
Back

xAI

Grok 3

Grok 3 is an xAI Grok model profile, part of xAI's assistant and reasoning model family for real-time, coding, and general-purpose AI workflows. The benchmark snapshot highlights how this Grok variant compares with competing frontier and open-weight models on capability, speed, latency, and cost.

xAI model releases

Operational Metrics

Output Speed52.2 tok/s
First Token0.50s
Blended Price$6.00/M

Model Metadata

Queryable facts extracted from the upstream model payload.

ReleaseFeb 19, 2025
Context Windown/a
Modalitiesn/a
API fields: release_date

Strength: TTFT

Rank #43 across 293 models.

0.50s

Watch Area: Output $

Rank #301 across 325 models.

$15.00/M

Watch Area: Value

Rank #298 across 323 models.

4.2

Watch Area: Blended $

Rank #299 across 325 models.

$6.00/M

Strength Profile

Percentile score by analysis domain.

* Cost is inverted: lower input, output, and blended prices rank higher.

Benchmark Percentiles

Higher bars mean stronger relative placement.

All Benchmarks

MetricDomainValueRank
Artificial Analysis Intelligence Indexoverall25.2#186
Artificial Analysis Coding Indexcoding19.8#194
Artificial Analysis Math Indexmath58.0#120
MMLU-Proreasoning79.9%#117
GPQA
reasoning
69.3%
#209
Humanity's Last Examreasoning5.1%#286
LiveCodeBenchcoding42.5%#171
SciCodecoding, reasoning36.8%#153
MATH-500math87.0%#88
AIMEmath33.0%#77
Output Speedspeed52.2 tok/s#215
Time to First Tokenspeed0.50s#43
Blended Pricecost$6.00/M#299
Input Pricecost$3.00/M#299
Output Pricecost$15.00/M#301
Value Indexcost, overall4.2#298