// head_to_head

GPT-5.2 vs SpaceXAI: Grok Build 0.1

Published LiveBench scores across all seven categories, live list pricing, context windows, and the measured cost of a point of capability — for both models, side by side.

OpenRouter + LiveBenchAll comparisonsFull leaderboard

GPT-5.2 scores higher, SpaceXAI: Grok Build 0.1 costs less — it depends on your workload.

GPT-5.2 is ahead by 6.9 points overall, and SpaceXAI: Grok Build 0.1 lists 3.9× cheaper per blended million tokens. Whether 6.9 points is worth that depends on how much a wrong answer costs you. SpaceXAI: Grok Build 0.1 also leads on measured cost per point of capability, at $0.0144 per point.

openai

GPT-5.2

Blended / 1M
$4.81
Context
400K
Released
Dec 10, 2025
Overall score
74.6
reasoningtool callingfile inputimage inputprompt caching

x-ai

SpaceXAI: Grok Build 0.1

Blended / 1M
$1.25
Context
256K
Released
May 20, 2026
Overall score
67.8
reasoningtool callingimage inputfile inputprompt caching

Specs and pricing

MetricGPT-5.2SpaceXAI: Grok Build 0.1
LiveBench overall

Mean of the seven LiveBench category scores, 0–100. Higher is better.

74.6win67.8
Cost per point

Measured benchmark spend divided by overall score — dollars per point of capability.

$0.1289$0.0144win
Blended price / 1M

3:1 input:output mix, the usual shape of production traffic.

$4.81$1.25win
Input price / 1M$1.75$1.00win
Output price / 1M$14.00$2.00win
Cached input / 1M

Price of an input token served from the prompt cache, where the provider publishes one.

$0.175win$0.200
Context window400Kwin256K
Max output tokens128K

Benchmarks by category

An overall score averages away the thing you probably care about. These are the seven LiveBench categories scored separately — GPT-5.2 on top, SpaceXAI: Grok Build 0.1 below, both out of 100.

Agentic coding
50.3
45.8
Coding
76.1
65.4
Reasoning
83.2
76.4
Mathematics
93.2
78.4
Data analysis
78.2
70.8
Language
79.8
72.5
Instruction following
61.8
65.2

What each one costs to run

Per-token prices are hard to feel. These are monthly list costs for both models across five workload shapes, using each provider's published cached-input rate where there is one.

WorkloadGPT-5.2SpaceXAI: Grok Build 0.1
Support chatbot

1.2K in / 400 out × 200K requests

$1426.60/mo$342.40/mo
RAG assistant

8K in / 600 out × 100K requests

$1610.00/mo$600.00/mo
Coding agent

40K in / 4K out × 20K requests

$1638.00/mo$512.00/mo
Document extraction

20K in / 1.5K out × 50K requests

$2721.25/mo$1110.00/mo
Bulk classification

500 in / 20 out × 5M requests

$4987.50/mo$2300.00/mo
Run these two through the cost calculator

Which should you pick?

You are running this at volume

SpaceXAI: Grok Build 0.1

Lowest measured cost per point of capability at $0.0144 per point — the gap compounds with every request.

Quality matters more than the bill

GPT-5.2

Highest overall LiveBench score of the two at 74.6.

The workload is coding or agentic work

GPT-5.2

Leads on agentic coding — 50.3 against 45.8.

You need to fit large documents in one call

GPT-5.2

Wider context window — 400K against 256K.

GPT-5.2 vs SpaceXAI: Grok Build 0.1 FAQ

Which is better, GPT-5.2 or SpaceXAI: Grok Build 0.1?

GPT-5.2 scores higher, SpaceXAI: Grok Build 0.1 costs less — it depends on your workload. GPT-5.2 is ahead by 6.9 points overall, and SpaceXAI: Grok Build 0.1 lists 3.9× cheaper per blended million tokens. Whether 6.9 points is worth that depends on how much a wrong answer costs you. SpaceXAI: Grok Build 0.1 also leads on measured cost per point of capability, at $0.0144 per point.

Is GPT-5.2 cheaper than SpaceXAI: Grok Build 0.1?

SpaceXAI: Grok Build 0.1 is cheaper. On a 3:1 input:output blend, GPT-5.2 lists at $4.81 per million tokens and SpaceXAI: Grok Build 0.1 at $1.25 — SpaceXAI: Grok Build 0.1 is 3.9× cheaper. Input and output are priced separately — GPT-5.2 charges $1.75 in and $14.00 out, SpaceXAI: Grok Build 0.1 charges $1.00 and $2.00 — so the model that looks cheaper flips depending on how output-heavy your workload is.

GPT-5.2 vs SpaceXAI: Grok Build 0.1: which scores higher on benchmarks?

GPT-5.2 scores 74.6 and SpaceXAI: Grok Build 0.1 scores 67.8 overall on LiveBench, the mean of its seven categories. That is a 6.9-point lead for GPT-5.2. Category scores differ from the overall figure — a model can lead on reasoning and trail on coding, which the per-category table above breaks out.

Which gives better value for money, GPT-5.2 or SpaceXAI: Grok Build 0.1?

SpaceXAI: Grok Build 0.1. Cost per point divides the measured dollars LiveBench spent running the benchmark by the score it earned, so it captures something token pricing misses: a reasoning model can emit many times more tokens than its per-token rate suggests. GPT-5.2 works out at $0.1289 per point and SpaceXAI: Grok Build 0.1 at $0.0144.

Does GPT-5.2 or SpaceXAI: Grok Build 0.1 have a bigger context window?

GPT-5.2 has the larger context window: 400K for GPT-5.2 against 256K for SpaceXAI: Grok Build 0.1. Note that a window you can fill is not a window you should fill — retrieval quality usually degrades well before the limit, and you pay for every token you put in it.

Do GPT-5.2 and SpaceXAI: Grok Build 0.1 support prompt caching?

Both publish a cached-input rate: $0.175 per million for GPT-5.2 and $0.200 for SpaceXAI: Grok Build 0.1, against full input rates of $1.75 and $1.00. On a workload with a long stable prefix — a system prompt, a tool schema, a retrieved corpus — that changes the economics more than the headline price does.

Related comparisons

How these numbers are produced

  • Price — provider list price from OpenRouter, refreshed every 15 minutes. “Blended” is a 3:1 input:output mix.
  • ScoresLiveBench release 2026-06-25, using their own category map. Each model shows its strongest published run. A blank means “not evaluated”, never “bad”.
  • Cost per point — the measured dollars LiveBench spent on the run, divided by the score it earned.
  • “Win” — awarded only past a threshold: one full point on a benchmark score, 10% on a price, 25% on a context window. Anything tighter reports as a tie, because effort settings alone move a LiveBench score by more than that.

Published benchmarks rank models on someone else's tasks. Before committing, see LLM & agent evaluation for building an eval on your own.