Gemini 3.1 Pro Preview vs GPT-5.4 Mini

GPT-5.4 Mini leads Gemini 3.1 Pro Preview on coding, 35.8 to 32.3 on the Vibe Coding Index, and GPT-5.4 Mini costs 2.7x less per output token ($4.50 vs $12.00 per million). Updated October 21, 2026; 86 benchmarks have a result for both.

Replace Gemini 3.1 Pro Preview Replace GPT-5.4 Mini

Gemini 3.1 Pro PreviewGoogle

Coding: 32.3
Overall: 54.0
Output $/M: $12.00

GPT-5.4 MiniOpenAI

Coding: 35.8
Overall: 44.0
Output $/M: $4.50

vs boards won of 86 shared, 2 tied

Gemini 3.1 Pro Preview or GPT-5.4 Mini: which to pick

Pick GPT-5.4 Mini for coding: it scores 35.8 on the Vibe Coding Index against 32.3 for Gemini 3.1 Pro Preview.

Pick Gemini 3.1 Pro Preview for a larger context window (1.05M against 400K tokens) and work measured by LMArena WebDev or AA Coding Index, where it leads.

Model AGemini 3.1 Pro PreviewGoogle32.3/1004 independent benchmarks$0.99 per solved task Model BGPT-5.4 MiniOpenAI35.8/1005 independent benchmarks$0.70 per solved task

86473

Shared results: 86
Gemini 3.1 Pro Preview only: 47
GPT-5.4 Mini only: 3
Like-for-like categories: 7 of 9

Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.

Which one for your work

Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.

Coding
Vibe Coding Index, six public coding benchmarks
GPT-5.4 Mini
GPT-5.4 Mini scores 35.8 against 32.3.
4 and 5 benchmarks behind the scores
Intelligence
AA Intelligence Index
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview leads, 29.7 against 24.1.
Same board, both measured
Agentic work
AA Agentic Index
GPT-5.4 Mini
GPT-5.4 Mini leads, 17.9 against 8.2.
Same board, both measured
Reasoning
GPQA Diamond
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview leads, 95.5% against 83.1%.
Same board, both measured
Math
AIME
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview leads, 98.1% against 95.6%.
Same board, both measured
Knowledge
MMLU Pro
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview leads, 91.0% against 84.5%.
Same board, both measured
Web design
Design Arena: websites
No call
Only Gemini 3.1 Pro Preview has a Design Arena: websites result, 1234.
Directional only
Long documents
Listed context window
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview takes 1.05M tokens against 400K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
GPT-5.4 Mini
Gemini 3.1 Pro Preview $0.0080, GPT-5.4 Mini $0.0030 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
GPT-5.4 Mini
Gemini 3.1 Pro Preview $0.99, GPT-5.4 Mini $0.70.
Published attempt cost and pass rate

At a glance

Coding index: Gemini 3.1 Pro Preview 32.3 from 4 benchmarks, GPT-5.4 Mini 35.8 from 5 benchmarks.
Widest category: Reasoning, 17.1 points apart on average over 14 shared benchmarks.
Widest single gap: ARC-AGI-2: Gemini 3.1 Pro Preview 77.1% against GPT-5.4 Mini 18.9%, 58.2 points apart on a 0 to 100 scale.
Output price: Gemini 3.1 Pro Preview $12.00 against GPT-5.4 Mini $4.50 per million output tokens, 2.7x apart.
Context window: Gemini 3.1 Pro Preview takes 1.05M tokens, GPT-5.4 Mini 400K.

Benchmark by benchmark

First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.

Boards won, where both have a result
Category	Gemini 3.1 Pro Preview	GPT-5.4 Mini	Ties
Coding	13	2	2 ties
Intelligence	1	0
Agentic work	5	2
Reasoning	14	0
Math	7	0
Knowledge	10	0
General	29	1
All shared boards	79	5	2 ties

CodingLike-for-likeSix of these boards feed the Vibe Coding Index132

Coding benchmarks for Gemini 3.1 Pro Preview and GPT-5.4 Mini
Benchmark	Gemini 3.1 Pro Preview	GPT-5.4 Mini	Leader
LMArena WebDev	1447	1397	Gemini 3.1 Pro Preview
AA Coding Index	68.8	56.1	Gemini 3.1 Pro Preview
LiveCodeBench (Vals AI)	88.5%	81.5%	Gemini 3.1 Pro Preview
SWE-bench Verified (Vals AI)	78.8%	73.0%	Gemini 3.1 Pro Preview
Terminal-Bench 4 (Vals AI)	2.5%	2.5%	Tie
Vibe Code Bench (Vals AI)	32.0%	48.0%	GPT-5.4 Mini
Code migration (Vals AI)	17.3%	12.9%	Gemini 3.1 Pro Preview
ProgramBench (Vals AI)	0.0%	0.0%	Tie
IOI (Vals AI)	51.8%	Not measured	Only Gemini 3.1 Pro Preview measured
Terminal-Bench 2.1 (Vals AI)	70.8%	54.7%	Gemini 3.1 Pro Preview
Vibe Code Bench 1-100 (Vals AI)	6.7%	Not measured	Only Gemini 3.1 Pro Preview measured
SciCode	58.7%	52.1%	Gemini 3.1 Pro Preview
Terminal-Bench Hard (Artificial Analysis run)	53.8%	52.3%	Gemini 3.1 Pro Preview
Terminal-Bench	80.2%	Not measured	Only Gemini 3.1 Pro Preview measured
FrontierCode	Not measured	27.0%	Only GPT-5.4 Mini measured
GSO-Bench	22.6%	Not measured	Only Gemini 3.1 Pro Preview measured
WeirdML	72.1%	60.3%	Gemini 3.1 Pro Preview
MirrorCode	8.9%	Not measured	Only Gemini 3.1 Pro Preview measured
ALE-Bench	1160.6	1188.6	GPT-5.4 Mini
LMArena Text: coding	1484	1438	Gemini 3.1 Pro Preview
LMArena Text: software and IT	1487	1436	Gemini 3.1 Pro Preview
LMArena WebDev: React	1438	1386	Gemini 3.1 Pro Preview
LMArena WebDev: HTML	1490	1419	Gemini 3.1 Pro Preview
LMArena WebDev: from an image	1481	Not measured	Only Gemini 3.1 Pro Preview measured
SciCode	14.3%	Not measured	Only Gemini 3.1 Pro Preview measured
Neither model has a result on the other 14 boards here

IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10

Intelligence benchmarks for Gemini 3.1 Pro Preview and GPT-5.4 Mini
Benchmark	Gemini 3.1 Pro Preview	GPT-5.4 Mini	Leader
AA Intelligence Index	29.7	24.1	Gemini 3.1 Pro Preview
Epoch Capabilities Index	Not measured	148.7	Only GPT-5.4 Mini measured

Agentic workLike-for-likePublic boards, shown as published, kept out of the index52

Agentic work benchmarks for Gemini 3.1 Pro Preview and GPT-5.4 Mini
Benchmark	Gemini 3.1 Pro Preview	GPT-5.4 Mini	Leader
AA Agentic Index	8.2	17.9	GPT-5.4 Mini
Design Arena: agents building web apps	1125	Not measured	Only Gemini 3.1 Pro Preview measured
Design Arena: agents building full-stack apps	1068	Not measured	Only Gemini 3.1 Pro Preview measured
Design Arena: agents building mobile apps	1093	Not measured	Only Gemini 3.1 Pro Preview measured
Design Arena: agents building Android apps	1048	Not measured	Only Gemini 3.1 Pro Preview measured
Design Arena: agents building Godot games	1236	Not measured	Only Gemini 3.1 Pro Preview measured
Design Arena: agents building games	1114	Not measured	Only Gemini 3.1 Pro Preview measured
Design Arena: HTML slides	1153	Not measured	Only Gemini 3.1 Pro Preview measured
Design Arena: PowerPoint slides	1066	Not measured	Only Gemini 3.1 Pro Preview measured
SREBench (Vals AI)	0.0%	Not measured	Only Gemini 3.1 Pro Preview measured
Finance Agent (Vals AI)	43.0%	45.4%	GPT-5.4 Mini
Tax Agent Bench (Vals AI)	9.3%	8.8%	Gemini 3.1 Pro Preview
Legal Research Bench (Vals AI)	20.7%	12.5%	Gemini 3.1 Pro Preview
Excel Modeling Benchmark (Vals AI)	52.6%	45.4%	Gemini 3.1 Pro Preview
BioMysteryBench (Vals AI)	60.0%	Not measured	Only Gemini 3.1 Pro Preview measured
Terminal-Bench-Science (Vals AI)	1.4%	Not measured	Only Gemini 3.1 Pro Preview measured
Vals Science Index	27.4%	Not measured	Only Gemini 3.1 Pro Preview measured
τ²-Bench Telecom	95.6%	83.3%	Gemini 3.1 Pro Preview
APEX-Agents	35.1%	Not measured	Only Gemini 3.1 Pro Preview measured
METR time horizons	77.0%	Not measured	Only Gemini 3.1 Pro Preview measured
BALROG	57.0%	Not measured	Only Gemini 3.1 Pro Preview measured
DeepResearch Bench	47.8%	36.3%	Gemini 3.1 Pro Preview
PostTrainBench	22.0%	Not measured	Only Gemini 3.1 Pro Preview measured
Vending-Bench 2	$911	Not measured	Only Gemini 3.1 Pro Preview measured
Neither model has a result on the other 17 boards here

ReasoningLike-for-likePublic boards, shown as published, kept out of the index140

Reasoning benchmarks for Gemini 3.1 Pro Preview and GPT-5.4 Mini
Benchmark	Gemini 3.1 Pro Preview	GPT-5.4 Mini	Leader
GPQA Diamond	95.5%	83.1%	Gemini 3.1 Pro Preview
MysteryMechanism (Vals AI)	20.7%	Not measured	Only Gemini 3.1 Pro Preview measured
MMMU Pro (Vals AI)	88.2%	79.3%	Gemini 3.1 Pro Preview
GPQA Diamond (Artificial Analysis run)	94.1%	87.5%	Gemini 3.1 Pro Preview
Humanity's Last Exam (Artificial Analysis run)	47.0%	28.1%	Gemini 3.1 Pro Preview
GPQA Diamond (Epoch AI run)	94.4%	86.9%	Gemini 3.1 Pro Preview
ARC-AGI	98.0%	63.7%	Gemini 3.1 Pro Preview
ARC-AGI-2	77.1%	18.9%	Gemini 3.1 Pro Preview
SimpleBench	79.6%	Not measured	Only Gemini 3.1 Pro Preview measured
Chess puzzles	51.0%	23.0%	Gemini 3.1 Pro Preview
Mystery game puzzles	34.0%	11.0%	Gemini 3.1 Pro Preview
EBR-bench	14.3%	Not measured	Only Gemini 3.1 Pro Preview measured
LMArena Text: hard prompts	1485	1424	Gemini 3.1 Pro Preview
LMArena Text: expert	1483	1435	Gemini 3.1 Pro Preview
LMArena Text: hard prompts in English	1480	1420	Gemini 3.1 Pro Preview
LMArena Vision: diagrams	1311	1266	Gemini 3.1 Pro Preview
LMArena Vision: homework	1316	1285	Gemini 3.1 Pro Preview
Kagi LLM Benchmark	Not measured	37.9%	Only GPT-5.4 Mini measured
Neither model has a result on the other 4 boards here

MathLike-for-likePublic boards, shown as published, kept out of the index70

Math benchmarks for Gemini 3.1 Pro Preview and GPT-5.4 Mini
Benchmark	Gemini 3.1 Pro Preview	GPT-5.4 Mini	Leader
AIME	98.1%	95.6%	Gemini 3.1 Pro Preview
OTIS Mock AIME	95.6%	88.9%	Gemini 3.1 Pro Preview
FrontierMath, tiers 1 to 3	59.6%	51.2%	Gemini 3.1 Pro Preview
FrontierMath, tier 4	26.8%	9.8%	Gemini 3.1 Pro Preview
ProofBench	26.0%	21.0%	Gemini 3.1 Pro Preview
LMArena Text: math	1486	1418	Gemini 3.1 Pro Preview
LMArena Text: mathematical work	1478	1429	Gemini 3.1 Pro Preview
Neither model has a result on the other 6 boards here

KnowledgeLike-for-likePublic boards, shown as published, kept out of the index100

Knowledge benchmarks for Gemini 3.1 Pro Preview and GPT-5.4 Mini
Benchmark	Gemini 3.1 Pro Preview	GPT-5.4 Mini	Leader
MMLU Pro	91.0%	84.5%	Gemini 3.1 Pro Preview
LegalBench (Vals AI)	87.4%	Not measured	Only Gemini 3.1 Pro Preview measured
CaseLaw (Vals AI)	64.8%	51.7%	Gemini 3.1 Pro Preview
CorpFin (Vals AI)	64.5%	60.9%	Gemini 3.1 Pro Preview
TaxEval (Vals AI)	72.9%	71.2%	Gemini 3.1 Pro Preview
MortgageTax (Vals AI)	69.4%	63.5%	Gemini 3.1 Pro Preview
MedQA (Vals AI)	96.4%	Not measured	Only Gemini 3.1 Pro Preview measured
MedCode (Vals AI)	59.1%	Not measured	Only Gemini 3.1 Pro Preview measured
SimpleQA Verified	73.5%	29.4%	Gemini 3.1 Pro Preview
LMArena Text: science	1497	1417	Gemini 3.1 Pro Preview
LMArena Text: medicine and healthcare	1486	1395	Gemini 3.1 Pro Preview
LMArena Text: legal and government	1487	1414	Gemini 3.1 Pro Preview
LMArena Text: business and finance	1459	1418	Gemini 3.1 Pro Preview
FACTS Benchmark Suite	67.4%	Not measured	Only Gemini 3.1 Pro Preview measured
Neither model has a result on the other 4 boards here

Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared

Web design benchmarks for Gemini 3.1 Pro Preview and GPT-5.4 Mini
Benchmark	Gemini 3.1 Pro Preview	GPT-5.4 Mini	Leader
Design Arena: websites	1234	Not measured	Only Gemini 3.1 Pro Preview measured
Design Arena: UI components	1227	Not measured	Only Gemini 3.1 Pro Preview measured
Design Arena: game dev	1203	Not measured	Only Gemini 3.1 Pro Preview measured
Design Arena: data viz	1209	Not measured	Only Gemini 3.1 Pro Preview measured
Design Arena: 3D	1234	Not measured	Only Gemini 3.1 Pro Preview measured
Design Arena: all code categories	1231	Not measured	Only Gemini 3.1 Pro Preview measured
Design Arena: SVG	1285	Not measured	Only Gemini 3.1 Pro Preview measured
Design Arena: ASCII art	1270	Not measured	Only Gemini 3.1 Pro Preview measured
Neither model has a result on the other 1 board here

GeneralLike-for-likePublic boards, shown as published, kept out of the index291

General benchmarks for Gemini 3.1 Pro Preview and GPT-5.4 Mini
Benchmark	Gemini 3.1 Pro Preview	GPT-5.4 Mini	Leader
Public Benefits Bench (Vals AI)	53.8%	Not measured	Only Gemini 3.1 Pro Preview measured
SAGE (Vals AI)	48.7%	50.8%	GPT-5.4 Mini
MedScribe (Vals AI)	76.1%	Not measured	Only Gemini 3.1 Pro Preview measured
Vals Multimodal Index	56.1%	54.2%	Gemini 3.1 Pro Preview
IFBench	77.1%	73.3%	Gemini 3.1 Pro Preview
Long context reasoning (AA-LCR)	82.0%	77.0%	Gemini 3.1 Pro Preview
DTBench	97.1%	80.0%	Gemini 3.1 Pro Preview
LMCA	53.8%	40.8%	Gemini 3.1 Pro Preview
CL-bench	20.8%	Not measured	Only Gemini 3.1 Pro Preview measured
Furniture assembly	26.7%	Not measured	Only Gemini 3.1 Pro Preview measured
ExploitBench	26.1%	Not measured	Only Gemini 3.1 Pro Preview measured
CL-bench Life	16.9%	Not measured	Only Gemini 3.1 Pro Preview measured
LMArena Text	1480	1412	Gemini 3.1 Pro Preview
LMArena Text: instruction following	1466	1405	Gemini 3.1 Pro Preview
LMArena Text: creative writing	1482	1370	Gemini 3.1 Pro Preview
LMArena Vision	1296	1245	Gemini 3.1 Pro Preview
LMArena Text: English	1478	1412	Gemini 3.1 Pro Preview
LMArena Text: non-English	1476	1405	Gemini 3.1 Pro Preview
LMArena Text: Chinese	1527	1446	Gemini 3.1 Pro Preview
LMArena Text: German	1490	1408	Gemini 3.1 Pro Preview
LMArena Text: Japanese	1491	1375	Gemini 3.1 Pro Preview
LMArena Text: Korean	1455	1370	Gemini 3.1 Pro Preview
LMArena Text: French	1487	1441	Gemini 3.1 Pro Preview
LMArena Text: Spanish	1481	1405	Gemini 3.1 Pro Preview
LMArena Text: Russian	1497	1417	Gemini 3.1 Pro Preview
LMArena Text: Polish	1498	1415	Gemini 3.1 Pro Preview
LMArena Text: multi-turn	1487	1429	Gemini 3.1 Pro Preview
LMArena Text: longer queries	1482	1408	Gemini 3.1 Pro Preview
LMArena Text: writing and language	1481	1393	Gemini 3.1 Pro Preview
LMArena Text: entertainment and media	1465	1373	Gemini 3.1 Pro Preview
LMArena Vision: English	1287	1244	Gemini 3.1 Pro Preview
LMArena Vision: Chinese	1364	1286	Gemini 3.1 Pro Preview
LMArena Vision: reading text	1304	1253	Gemini 3.1 Pro Preview
LMArena Vision: humor	1322	1235	Gemini 3.1 Pro Preview
LMArena Vision: captioning	1345	Not measured	Only Gemini 3.1 Pro Preview measured
LMArena Vision: recognizing things	1330	1218	Gemini 3.1 Pro Preview
LMArena Vision: creative writing	1324	1222	Gemini 3.1 Pro Preview
LMArena Document	1444	Not measured	Only Gemini 3.1 Pro Preview measured
Neither model has a result on the other 8 boards here

Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared

Image generation benchmarks for Gemini 3.1 Pro Preview and GPT-5.4 Mini
Benchmark	Gemini 3.1 Pro Preview	GPT-5.4 Mini	Leader
Neither model has a result on 5 boards here

What each workload costs

Three fixed token mixes at each model's listed price, so per-token rates become a bill.

Chat turn

1K input + 500 output tokens

Gemini 3.1 Pro Preview$0.0080Fits in one request

GPT-5.4 Mini$0.0030Fits in one request

GPT-5.4 Mini costs less

Repository review

50K input + 3K output tokens

Gemini 3.1 Pro Preview$0.136Fits in one request

GPT-5.4 Mini$0.051Fits in one request

GPT-5.4 Mini costs less

Agent loop

200K input + 10K output tokens

Gemini 3.1 Pro Preview$0.520Fits in one request

GPT-5.4 Mini$0.195Fits in one request

GPT-5.4 Mini costs less

Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.

Specification differences

The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.

Specifications of Gemini 3.1 Pro Preview and GPT-5.4 Mini
Specification	Google Gemini 3.1 Pro Preview	OpenAI GPT-5.4 Mini
Maker	Google	OpenAI
Weights	No public weights listed	No public weights listed
Released	February 19, 2026	March 17, 2026
Context window	1.05M	400K
Input $/Mtok	$2.00	$0.75
Output $/Mtok	$12.00	$4.50
Coding index	32.3	35.8
Independent measurements behind it	4	5
Cost per solved task	$0.99	$0.70
Source	OpenRouter listing	OpenRouter listing

Questions

Is Gemini 3.1 Pro Preview better than GPT-5.4 Mini for coding?

Pick GPT-5.4 Mini for coding: it scores 35.8 on the Vibe Coding Index against 32.3 for Gemini 3.1 Pro Preview. Pick Gemini 3.1 Pro Preview for a larger context window (1.05M against 400K tokens) and work measured by LMArena WebDev or AA Coding Index, where it leads.

Which is cheaper, Gemini 3.1 Pro Preview or GPT-5.4 Mini?

Gemini 3.1 Pro Preview costs $2.00 per million input tokens and $12.00 per million output tokens; GPT-5.4 Mini costs $0.75 and $4.50. Per solved SWE-bench Verified task, Gemini 3.1 Pro Preview costs $0.99 and GPT-5.4 Mini $0.70.

Which has the bigger context window, Gemini 3.1 Pro Preview or GPT-5.4 Mini?

Gemini 3.1 Pro Preview, with 1.05M tokens against 400K.

How many benchmarks is the Gemini 3.1 Pro Preview vs GPT-5.4 Mini comparison based on?

86 benchmarks have a result for both models as of October 21, 2026. Gemini 3.1 Pro Preview's coding index rests on 4 independent benchmarks and GPT-5.4 Mini's on 5. Where only one model has a result, the page says so instead of naming a winner.

Compare next

Embed this comparison on your site

Free under CC BY 4.0, while the source link stays visible. Preview the frame · Terms and other embeds

<iframe src="https://llmbenchmark.ai/embed/compare/gemini-3-1-pro-preview-vs-gpt-5-4-mini" title="Gemini 3.1 Pro Preview vs GPT-5.4 Mini, LLMBenchmark.ai" width="100%" height="360" style="border:0;max-width:100%" loading="lazy"></iframe>
<p style="font:13px/1.4 sans-serif;margin:6px 0 0">Source: <a href="https://llmbenchmark.ai/compare/gemini-3-1-pro-preview-vs-gpt-5-4-mini">LLMBenchmark.ai, Gemini 3.1 Pro Preview vs GPT-5.4 Mini</a></p>

Gemini 3.1 Pro Preview or GPT-5.4 Mini: which to pick

Which one for your work

Coding

Intelligence

Agentic work

Reasoning

Math

Knowledge

Web design

Long documents

Everyday cost

Cost per solved task

At a glance

Benchmark by benchmark

What each workload costs

Chat turn

Repository review

Agent loop

Specification differences

Questions

Compare next