Gemini 3.1 Pro Preview vs GPT-5.4

GPT-5.4 leads Gemini 3.1 Pro Preview on coding, 64.4 to 32.3 on the Vibe Coding Index, and Gemini 3.1 Pro Preview costs 1.3x less per output token ($12.00 vs $15.00 per million). Updated October 21, 2026; 107 benchmarks have a result for both.

Replace Gemini 3.1 Pro Preview Replace GPT-5.4

Gemini 3.1 Pro PreviewGoogle

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

GPT-5.4OpenAI

Coding: 64.4
Overall: 69.6
Output $/M: $15.00

vs boards won of 107 shared, 1 tied

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

Pick GPT-5.4 for coding: it scores 64.4 on the Vibe Coding Index against 32.3 for Gemini 3.1 Pro Preview, though on 3 benchmarks against 4.

Pick Gemini 3.1 Pro Preview for output tokens 1.3x cheaper ($12.00 vs $15.00 per million) and a lower cost per solved task ($0.99 against $1.02).

Model AGemini 3.1 Pro PreviewGoogle32.3/1004 independent benchmarks$0.99 per solved task Model BGPT-5.4OpenAI64.4/1003 independent benchmarks$1.02 per solved task

107263

Shared results: 107
Gemini 3.1 Pro Preview only: 26
GPT-5.4 only: 3
Like-for-like categories: 8 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
GPT-5.4 scores 64.4 against 32.3.
4 and 3 benchmarks behind the scores
Intelligence
AA Intelligence Index
GPT-5.4
GPT-5.4 leads, 39.0 against 29.7.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Gemini 3.1 Pro Preview has a AA Agentic Index result, 8.2.
Directional only
Reasoning
GPQA Diamond
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview leads, 95.5% against 91.7%.
Same board, both measured
Math
AIME
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview leads, 98.1% against 96.7%.
Same board, both measured
Knowledge
MMLU Pro
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview leads, 91.0% against 87.5%.
Same board, both measured
Web design
Design Arena: websites
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview leads, 1234 against 1199.
Same board, both measured
Long documents
Listed context window
GPT-5.4
GPT-5.4 takes 1.05M tokens against 1.05M.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview $0.0080, GPT-5.4 $0.010 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview $0.99, GPT-5.4 $1.02.
Published attempt cost and pass rate

At a glance

Coding index: Gemini 3.1 Pro Preview 32.3 from 4 benchmarks, GPT-5.4 64.4 from 3 benchmarks.
Widest category: Math, 11.2 points apart on average over 7 shared benchmarks.
Widest single gap: Vibe Code Bench (Vals AI): Gemini 3.1 Pro Preview 32.0% against GPT-5.4 67.4%, 35.4 points apart on a 0 to 100 scale.
Output price: Gemini 3.1 Pro Preview $12.00 against GPT-5.4 $15.00 per million output tokens, 1.3x apart.
Context window: Gemini 3.1 Pro Preview takes 1.05M tokens, GPT-5.4 1.05M.

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	Ties
Coding	4	14
Intelligence	0	1
Agentic work	9	2
Reasoning	9	6
Math	1	6
Knowledge	10	3
Web design	8	0
General	23	10	1 tie
All shared boards	64	42	1 tie

CodingLike-for-likeSix of these boards feed the Vibe Coding Index414

Coding benchmarks for Gemini 3.1 Pro Preview and GPT-5.4
Benchmark	Gemini 3.1 Pro Preview	GPT-5.4	Leader
LMArena WebDev	1447	1464	GPT-5.4
AA Coding Index	68.8	71.1	GPT-5.4
LiveCodeBench (Vals AI)	88.5%	84.1%	Gemini 3.1 Pro Preview
SWE-bench Verified (Vals AI)	78.8%	78.2%	Gemini 3.1 Pro Preview
Terminal-Bench 4 (Vals AI)	2.5%	Not measured	Only Gemini 3.1 Pro Preview measured
Vibe Code Bench (Vals AI)	32.0%	67.4%	GPT-5.4
Code migration (Vals AI)	17.3%	35.0%	GPT-5.4
ProgramBench (Vals AI)	0.0%	0.5%	GPT-5.4
IOI (Vals AI)	51.8%	Not measured	Only Gemini 3.1 Pro Preview measured
Terminal-Bench 2.1 (Vals AI)	70.8%	Not measured	Only Gemini 3.1 Pro Preview measured
Vibe Code Bench 1-100 (Vals AI)	6.7%	Not measured	Only Gemini 3.1 Pro Preview measured
SkillsBench (Vals AI)	Not measured	51.7%	Only GPT-5.4 measured
SciCode	58.7%	Not measured	Only Gemini 3.1 Pro Preview measured
Terminal-Bench Hard (Artificial Analysis run)	53.8%	57.6%	GPT-5.4
Terminal-Bench	80.2%	81.8%	GPT-5.4
GSO-Bench	22.6%	31.4%	GPT-5.4
WeirdML	72.1%	77.7%	GPT-5.4
MirrorCode	8.9%	15.6%	GPT-5.4
ALE-Bench	1160.6	1607.0	GPT-5.4
LMArena Text: coding	1484	1496	GPT-5.4
LMArena Text: software and IT	1487	1491	GPT-5.4
LMArena WebDev: React	1438	1454	GPT-5.4
LMArena WebDev: HTML	1490	1478	Gemini 3.1 Pro Preview
LMArena WebDev: from an image	1481	1436	Gemini 3.1 Pro Preview
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 index01

Intelligence benchmarks for Gemini 3.1 Pro Preview and GPT-5.4
Benchmark	Gemini 3.1 Pro Preview	GPT-5.4	Leader
AA Intelligence Index	29.7	39.0	GPT-5.4
Epoch Capabilities Index	Not measured	157.3	Only GPT-5.4 measured

Agentic workLike-for-likePublic boards, shown as published, kept out of the index92

Agentic work benchmarks for Gemini 3.1 Pro Preview and GPT-5.4
Benchmark	Gemini 3.1 Pro Preview	GPT-5.4	Leader
AA Agentic Index	8.2	Not measured	Only Gemini 3.1 Pro Preview measured
Design Arena: agents building web apps	1125	1059	Gemini 3.1 Pro Preview
Design Arena: agents building full-stack apps	1068	1017	Gemini 3.1 Pro Preview
Design Arena: agents building mobile apps	1093	1087	Gemini 3.1 Pro Preview
Design Arena: agents building Android apps	1048	1030	Gemini 3.1 Pro Preview
Design Arena: agents building Godot games	1236	1135	Gemini 3.1 Pro Preview
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%	Not measured	Only Gemini 3.1 Pro Preview measured
Tax Agent Bench (Vals AI)	9.3%	Not measured	Only Gemini 3.1 Pro Preview measured
Legal Research Bench (Vals AI)	20.7%	Not measured	Only Gemini 3.1 Pro Preview measured
Excel Modeling Benchmark (Vals AI)	52.6%	Not measured	Only Gemini 3.1 Pro Preview measured
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%	87.1%	Gemini 3.1 Pro Preview
APEX-Agents	35.1%	52.4%	GPT-5.4
METR time horizons	77.0%	74.3%	Gemini 3.1 Pro Preview
BALROG	57.0%	Not measured	Only Gemini 3.1 Pro Preview measured
DeepResearch Bench	47.8%	35.1%	Gemini 3.1 Pro Preview
PostTrainBench	22.0%	19.0%	Gemini 3.1 Pro Preview
Vending-Bench 2	$911	$6,144	GPT-5.4
Neither model has a result on the other 17 boards here

ReasoningLike-for-likePublic boards, shown as published, kept out of the index96

Reasoning benchmarks for Gemini 3.1 Pro Preview and GPT-5.4
Benchmark	Gemini 3.1 Pro Preview	GPT-5.4	Leader
GPQA Diamond	95.5%	91.7%	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%	87.5%	Gemini 3.1 Pro Preview
GPQA Diamond (Artificial Analysis run)	94.1%	92.0%	Gemini 3.1 Pro Preview
Humanity's Last Exam (Artificial Analysis run)	47.0%	43.7%	Gemini 3.1 Pro Preview
GPQA Diamond (Epoch AI run)	94.4%	93.3%	Gemini 3.1 Pro Preview
ARC-AGI	98.0%	93.7%	Gemini 3.1 Pro Preview
ARC-AGI-2	77.1%	74.0%	Gemini 3.1 Pro Preview
SimpleBench	79.6%	Not measured	Only Gemini 3.1 Pro Preview measured
Chess puzzles	51.0%	48.0%	Gemini 3.1 Pro Preview
Mystery game puzzles	34.0%	37.0%	GPT-5.4
EBR-bench	14.3%	25.4%	GPT-5.4
LMArena Text: hard prompts	1485	1485	GPT-5.4
LMArena Text: expert	1483	1507	GPT-5.4
LMArena Text: hard prompts in English	1480	1479	Gemini 3.1 Pro Preview
LMArena Vision: diagrams	1311	1327	GPT-5.4
LMArena Vision: homework	1316	1336	GPT-5.4
Kagi LLM Benchmark	Not measured	63.8%	Only GPT-5.4 measured
Neither model has a result on the other 4 boards here

MathLike-for-likePublic boards, shown as published, kept out of the index16

Math benchmarks for Gemini 3.1 Pro Preview and GPT-5.4
Benchmark	Gemini 3.1 Pro Preview	GPT-5.4	Leader
AIME	98.1%	96.7%	Gemini 3.1 Pro Preview
OTIS Mock AIME	95.6%	97.8%	GPT-5.4
FrontierMath, tiers 1 to 3	59.6%	78.6%	GPT-5.4
FrontierMath, tier 4	26.8%	49.0%	GPT-5.4
ProofBench	26.0%	56.0%	GPT-5.4
LMArena Text: math	1486	1488	GPT-5.4
LMArena Text: mathematical work	1478	1497	GPT-5.4
Neither model has a result on the other 6 boards here

KnowledgeLike-for-likePublic boards, shown as published, kept out of the index103

Knowledge benchmarks for Gemini 3.1 Pro Preview and GPT-5.4
Benchmark	Gemini 3.1 Pro Preview	GPT-5.4	Leader
MMLU Pro	91.0%	87.5%	Gemini 3.1 Pro Preview
LegalBench (Vals AI)	87.4%	86.0%	Gemini 3.1 Pro Preview
CaseLaw (Vals AI)	64.8%	63.8%	Gemini 3.1 Pro Preview
CorpFin (Vals AI)	64.5%	65.3%	GPT-5.4
TaxEval (Vals AI)	72.9%	74.0%	GPT-5.4
MortgageTax (Vals AI)	69.4%	68.3%	Gemini 3.1 Pro Preview
MedQA (Vals AI)	96.4%	96.1%	Gemini 3.1 Pro Preview
MedCode (Vals AI)	59.1%	41.3%	Gemini 3.1 Pro Preview
SimpleQA Verified	73.5%	45.1%	Gemini 3.1 Pro Preview
LMArena Text: science	1497	1479	Gemini 3.1 Pro Preview
LMArena Text: medicine and healthcare	1486	1458	Gemini 3.1 Pro Preview
LMArena Text: legal and government	1487	1486	Gemini 3.1 Pro Preview
LMArena Text: business and finance	1459	1474	GPT-5.4
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 designLike-for-likePublic boards, shown as published, kept out of the index80

Web design benchmarks for Gemini 3.1 Pro Preview and GPT-5.4
Benchmark	Gemini 3.1 Pro Preview	GPT-5.4	Leader
Design Arena: websites	1234	1199	Gemini 3.1 Pro Preview
Design Arena: UI components	1227	1215	Gemini 3.1 Pro Preview
Design Arena: game dev	1203	1195	Gemini 3.1 Pro Preview
Design Arena: data viz	1209	1196	Gemini 3.1 Pro Preview
Design Arena: 3D	1234	1066	Gemini 3.1 Pro Preview
Design Arena: all code categories	1231	1180	Gemini 3.1 Pro Preview
Design Arena: SVG	1285	1142	Gemini 3.1 Pro Preview
Design Arena: ASCII art	1270	1188	Gemini 3.1 Pro Preview
Neither model has a result on the other 1 board here

GeneralLike-for-likePublic boards, shown as published, kept out of the index2310

General benchmarks for Gemini 3.1 Pro Preview and GPT-5.4
Benchmark	Gemini 3.1 Pro Preview	GPT-5.4	Leader
Public Benefits Bench (Vals AI)	53.8%	Not measured	Only Gemini 3.1 Pro Preview measured
SAGE (Vals AI)	48.7%	43.3%	Gemini 3.1 Pro Preview
MedScribe (Vals AI)	76.1%	77.5%	GPT-5.4
Vals Multimodal Index	56.1%	Not measured	Only Gemini 3.1 Pro Preview measured
IFBench	77.1%	73.9%	Gemini 3.1 Pro Preview
Long context reasoning (AA-LCR)	82.0%	82.0%	Tie
DTBench	97.1%	94.4%	Gemini 3.1 Pro Preview
LMCA	53.8%	52.0%	Gemini 3.1 Pro Preview
CL-bench	20.8%	27.9%	GPT-5.4
Furniture assembly	26.7%	37.5%	GPT-5.4
ExploitBench	26.1%	Not measured	Only Gemini 3.1 Pro Preview measured
CL-bench Life	16.9%	21.7%	GPT-5.4
LMArena Text	1480	1469	Gemini 3.1 Pro Preview
LMArena Text: instruction following	1466	1469	GPT-5.4
LMArena Text: creative writing	1482	1439	Gemini 3.1 Pro Preview
LMArena Vision	1296	1303	GPT-5.4
LMArena Text: English	1478	1467	Gemini 3.1 Pro Preview
LMArena Text: non-English	1476	1465	Gemini 3.1 Pro Preview
LMArena Text: Chinese	1527	1520	Gemini 3.1 Pro Preview
LMArena Text: German	1490	1472	Gemini 3.1 Pro Preview
LMArena Text: Japanese	1491	1485	Gemini 3.1 Pro Preview
LMArena Text: Korean	1455	1449	Gemini 3.1 Pro Preview
LMArena Text: French	1487	1493	GPT-5.4
LMArena Text: Spanish	1481	1452	Gemini 3.1 Pro Preview
LMArena Text: Russian	1497	1480	Gemini 3.1 Pro Preview
LMArena Text: Polish	1498	1472	Gemini 3.1 Pro Preview
LMArena Text: multi-turn	1487	1482	Gemini 3.1 Pro Preview
LMArena Text: longer queries	1482	1473	Gemini 3.1 Pro Preview
LMArena Text: writing and language	1481	1458	Gemini 3.1 Pro Preview
LMArena Text: entertainment and media	1465	1438	Gemini 3.1 Pro Preview
LMArena Vision: English	1287	1301	GPT-5.4
LMArena Vision: Chinese	1364	1354	Gemini 3.1 Pro Preview
LMArena Vision: reading text	1304	1312	GPT-5.4
LMArena Vision: humor	1322	1284	Gemini 3.1 Pro Preview
LMArena Vision: captioning	1345	Not measured	Only Gemini 3.1 Pro Preview measured
LMArena Vision: recognizing things	1330	1251	Gemini 3.1 Pro Preview
LMArena Vision: creative writing	1324	1283	Gemini 3.1 Pro Preview
LMArena Document	1444	1471	GPT-5.4
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
Benchmark	Gemini 3.1 Pro Preview	GPT-5.4	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$0.010Fits in one request

Gemini 3.1 Pro Preview costs less

Repository review

50K input + 3K output tokens

Gemini 3.1 Pro Preview$0.136Fits in one request

GPT-5.4$0.170Fits in one request

Gemini 3.1 Pro Preview costs less

Agent loop

200K input + 10K output tokens

Gemini 3.1 Pro Preview$0.520Fits in one request

GPT-5.4$0.650Fits in one request

Gemini 3.1 Pro Preview 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
Specification	Google Gemini 3.1 Pro Preview	OpenAI GPT-5.4
Maker	Google	OpenAI
Weights	No public weights listed	No public weights listed
Released	February 19, 2026	March 5, 2026
Context window	1.05M	1.05M
Input $/Mtok	$2.00	$2.50
Output $/Mtok	$12.00	$15.00
Coding index	32.3	64.4
Independent measurements behind it	4	3
Cost per solved task	$0.99	$1.02
Source	OpenRouter listing	OpenRouter listing

Questions

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

Pick GPT-5.4 for coding: it scores 64.4 on the Vibe Coding Index against 32.3 for Gemini 3.1 Pro Preview, though on 3 benchmarks against 4. Pick Gemini 3.1 Pro Preview for output tokens 1.3x cheaper ($12.00 vs $15.00 per million) and a lower cost per solved task ($0.99 against $1.02).

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

Gemini 3.1 Pro Preview costs $2.00 per million input tokens and $12.00 per million output tokens; GPT-5.4 costs $2.50 and $15.00. Per solved SWE-bench Verified task, Gemini 3.1 Pro Preview costs $0.99 and GPT-5.4 $1.02.

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

GPT-5.4, with 1.05M tokens against 1.05M.

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

107 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's on 3. 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" title="Gemini 3.1 Pro Preview vs GPT-5.4, 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">LLMBenchmark.ai, Gemini 3.1 Pro Preview vs GPT-5.4</a></p>

Gemini 3.1 Pro Preview or GPT-5.4: 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