// head_to_head

Gemini 3.1 Pro Preview vs GPT-5.2

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

Gemini 3.1 Pro Preview is the better model, at roughly the same price.

Gemini 3.1 Pro Preview leads by 2.3 points overall and the two list within about 10% of each other, so the cheaper-but-weaker trade-off does not apply. Price parity plus a score gap usually makes this an easy call. GPT-5.2 also leads on measured cost per point of capability, at $0.1289 per point.

google

Gemini 3.1 Pro Preview

Blended / 1M
$4.50
Context
1.0M
Released
Feb 19, 2026
Overall score
77.0
reasoningtool callingaudio inputfile inputimage inputvideo inputprompt caching

openai

GPT-5.2

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

Specs and pricing

MetricGemini 3.1 Pro PreviewGPT-5.2
LiveBench overall

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

77.0win74.6
Cost per point

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

$0.1567$0.1289win
Blended price / 1M

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

$4.50$4.81
Input price / 1M$2.00$1.75win
Output price / 1M$12.00win$14.00
Cached input / 1M

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

$0.200$0.175win
Context window1.0Mwin400K
Max output tokens66K128Kwin

Benchmarks by category

An overall score averages away the thing you probably care about. These are the seven LiveBench categories scored separately — Gemini 3.1 Pro Preview on top, GPT-5.2 below, both out of 100.

Agentic coding
44.1
50.3
Codingtoo close to call
76.5
76.1
Reasoningtoo close to call
84.0
83.2
Mathematics
91.0
93.2
Data analysistoo close to call
78.5
78.2
Language
85.4
79.8
Instruction following
79.1
61.8

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.

WorkloadGemini 3.1 Pro PreviewGPT-5.2
Support chatbot

1.2K in / 400 out × 200K requests

$1310.40/mo$1426.60/mo
RAG assistant

8K in / 600 out × 100K requests

$1600.00/mo$1610.00/mo
Coding agent

40K in / 4K out × 20K requests

$1552.00/mo$1638.00/mo
Document extraction

20K in / 1.5K out × 50K requests

$2810.00/mo$2721.25/mo
Bulk classification

500 in / 20 out × 5M requests

$5300.00/mo$4987.50/mo
Run these two through the cost calculator

Which should you pick?

You are running this at volume

GPT-5.2

Lowest measured cost per point of capability at $0.1289 per point — the gap compounds with every request.

Quality matters more than the bill

Gemini 3.1 Pro Preview

Highest overall LiveBench score of the two at 77.0.

The workload is coding or agentic work

GPT-5.2

Leads on agentic coding — 50.3 against 44.1.

You need to fit large documents in one call

Gemini 3.1 Pro Preview

Wider context window — 1.0M against 400K.

Gemini 3.1 Pro Preview vs GPT-5.2 FAQ

Which is better, Gemini 3.1 Pro Preview or GPT-5.2?

Gemini 3.1 Pro Preview is the better model, at roughly the same price. Gemini 3.1 Pro Preview leads by 2.3 points overall and the two list within about 10% of each other, so the cheaper-but-weaker trade-off does not apply. Price parity plus a score gap usually makes this an easy call. GPT-5.2 also leads on measured cost per point of capability, at $0.1289 per point.

Is Gemini 3.1 Pro Preview cheaper than GPT-5.2?

They cost about the same. Both land near $4.50 per million tokens on a 3:1 input:output blend, so price is unlikely to be the deciding factor between them.

Gemini 3.1 Pro Preview vs GPT-5.2: which scores higher on benchmarks?

Gemini 3.1 Pro Preview scores 77.0 and GPT-5.2 scores 74.6 overall on LiveBench, the mean of its seven categories. That is a 2.3-point lead for Gemini 3.1 Pro Preview. 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, Gemini 3.1 Pro Preview or GPT-5.2?

GPT-5.2. 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. Gemini 3.1 Pro Preview works out at $0.1567 per point and GPT-5.2 at $0.1289.

Does Gemini 3.1 Pro Preview or GPT-5.2 have a bigger context window?

Gemini 3.1 Pro Preview has the larger context window: 1.0M for Gemini 3.1 Pro Preview against 400K for GPT-5.2. 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 Gemini 3.1 Pro Preview and GPT-5.2 support prompt caching?

Both publish a cached-input rate: $0.200 per million for Gemini 3.1 Pro Preview and $0.175 for GPT-5.2, against full input rates of $2.00 and $1.75. 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.