Skip to content
llmwaves

Grok 4.5

xAI · released Jul 8, 2026

ProprietaryReasoningTool useStructured outputVision

Grok 4.5 is SpaceXAI's smartest model with frontier performance on coding, knowledge work, and STEM.

Specification

Context window
500K
Max output
Knowledge cutoff
Not stated
Parameters
Undisclosed
Licence
Proprietary
Serving providers
1
Moderated
No
Uptime
100.0%

Intelligence

55.8

98th percentile

Coding

72.4

Coding Index

Agentic

48.9

Agentic Index

Output speed

52 t/s

Median across providers

Latency

925ms

Time to first token

Cost per task

$0.58

Estimated

Benchmarks

Where the score comes from

The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.

Evaluation scores

Percentage correct · higher is better

  • GPQA Diamond
    93.1%
  • AA-LCR (long context)
    74.0%
  • SciCode
    54.1%
  • Humanity's Last Exam
    42.7%
  • τ²-bench (Telecom)
    42.1%

An evaluation missing from this list was not run for this model — it is not a zero.

View as table
EvaluationScore
GPQA Diamond93.1%
AA-LCR (long context)74.0%
SciCode54.1%
Humanity's Last Exam42.7%
τ²-bench (Telecom)42.1%

Against its peers

Intelligence Index · this model highlighted, nearest peers in grey

Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.

View as table
ModelIntelligence
Qwen3.8 Max58.1
Claude Opus 4.857.3
Muse Spark 1.256.8
GPT-5.6 Terra56.6
GPT-5.556.3
Grok 4.555.8
Claude Sonnet 555.3
Claude Opus 4.755.0

Percentile among all indexed models

Intelligence98th
Coding93th
Agentic87th

Pricing

What it costs to run

List prices per million tokens, plus what one representative task works out to.

List price

Input / 1M tokens
$2
Output / 1M tokens
$6
Cached input / 1M
$0.3
Blended 3:1
$3

One task, estimated

$0.58

Input tokens
50,000
Output tokens
80,000
Profile
Reasoning

Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).

Serving providers

Speed and latency figures are medians across these providers, so a widely-served model reports a blend rather than any single endpoint.