Gemini 3.8 Flash vs GPT-5.4 Mini

Updated October 21, 2026. 79 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Gemini 3.8 Flash Replace GPT-5.4 Mini

Gemini 3.8 FlashGoogle

Coding: 70.5
Overall: 40.9
Output $/M: $4.125

GPT-5.4 MiniOpenAI

Coding: 28.2
Overall: 24.1
Output $/M: $4.50

vs boards won of 79 shared

Decision reading

Pick Gemini 3.8 Flash for coding: it scores 70.5 on the Vibe Coding Index against 28.2 for GPT-5.4 Mini.

Pick GPT-5.4 Mini when a solved task costs $0.70 against $2.74, or when the benchmark that matters is SAGE (Vals AI), where it leads.

Model AGemini 3.8 FlashGoogle70.5/1002 independent benchmarks$2.74 per solved task Model BGPT-5.4 MiniOpenAI28.2/1001 independent benchmark$0.70 per solved task

79479

Shared results: 79
Gemini 3.8 Flash only: 47
GPT-5.4 Mini only: 9
Like-for-like categories: 7 of 9

Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.

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, four public coding benchmarks
Gemini 3.8 Flash
Gemini 3.8 Flash scores 70.5 against 28.2.
2 and 1 benchmarks behind the scores
Intelligence
AA Intelligence Index
Gemini 3.8 Flash
Gemini 3.8 Flash leads, 40.9 against 24.1.
Same board, both measured
Agentic work
AA Agentic Index
Gemini 3.8 Flash
Gemini 3.8 Flash leads, 40.2 against 17.9.
Same board, both measured
Reasoning
GPQA Diamond
Gemini 3.8 Flash
Gemini 3.8 Flash leads, 94.4% against 83.1%.
Same board, both measured
Math
AIME
No call
Only GPT-5.4 Mini has a AIME result, 95.6%.
Directional only
Knowledge
MMLU Pro
Gemini 3.8 Flash
Gemini 3.8 Flash leads, 90.2% against 84.5%.
Same board, both measured
Web design
Design Arena: websites
No call
Only Gemini 3.8 Flash has a Design Arena: websites result, 1301.
Directional only
General
Vals Index
No call
Only Gemini 3.8 Flash has a Vals Index result, 56.0%.
Directional only
Long documents
Listed context window
Gemini 3.8 Flash
Gemini 3.8 Flash takes 1.05M tokens against 400K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Gemini 3.8 Flash
Gemini 3.8 Flash $0.0029, 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 3.8 Flash $2.74, GPT-5.4 Mini $0.70.
Published attempt cost and pass rate

At a glance

Coding index: Gemini 3.8 Flash 70.5 from 2 benchmarks, GPT-5.4 Mini 28.2 from 1 benchmark.
Widest category: Agentic work, 23.0 points apart on average over 5 shared benchmarks.
Widest single gap: ARC-AGI-2: Gemini 3.8 Flash 89.2% against GPT-5.4 Mini 18.9%, 70.3 points apart on a 0 to 100 scale.
Output price: Gemini 3.8 Flash $4.125 against GPT-5.4 Mini $4.50 per million output tokens, 1.1x apart.
Context window: Gemini 3.8 Flash 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 3.8 Flash	GPT-5.4 Mini
Coding	17	0
Intelligence	2	0
Agentic work	5	0
Reasoning	14	0
Math	6	0
Knowledge	8	0
General	26	1
All shared boards	78	1

CodingLike-for-likeFour of these boards feed the Vibe Coding Index170

Coding benchmarks for Gemini 3.8 Flash and GPT-5.4 Mini
Benchmark	Gemini 3.8 Flash	GPT-5.4 Mini	Leader
LiveBench coding	82.2%	Not measured	Only Gemini 3.8 Flash measured
LMArena WebDev	1585	1397	Gemini 3.8 Flash
AA Coding Index	76.3	56.1	Gemini 3.8 Flash
LiveCodeBench (Vals AI)	89.5%	81.5%	Gemini 3.8 Flash
SWE-bench Verified (Vals AI)	80.0%	73.0%	Gemini 3.8 Flash
Terminal-Bench 4 (Vals AI)	19.7%	2.5%	Gemini 3.8 Flash
Vibe Code Bench (Vals AI)	78.7%	48.0%	Gemini 3.8 Flash
Code migration (Vals AI)	36.5%	12.9%	Gemini 3.8 Flash
ProgramBench (Vals AI)	1.0%	0.0%	Gemini 3.8 Flash
IOI (Vals AI)	56.9%	Not measured	Only Gemini 3.8 Flash measured
Terminal-Bench 2.1 (Vals AI)	81.3%	54.7%	Gemini 3.8 Flash
SWE-bench Multimodal (Vals AI)	40.8%	Not measured	Only Gemini 3.8 Flash measured
Vibe Code Bench 1-100 (Vals AI)	18.8%	Not measured	Only Gemini 3.8 Flash measured
SkillsBench (Vals AI)	58.0%	Not measured	Only Gemini 3.8 Flash measured
CyberBench (Vals AI)	43.8%	Not measured	Only Gemini 3.8 Flash measured
SciCode	56.6%	52.1%	Gemini 3.8 Flash
Terminal-Bench Hard (Artificial Analysis run)	Not measured	52.3%	Only GPT-5.4 Mini measured
FrontierCode	41.2%	27.0%	Gemini 3.8 Flash
FrontierSWE	19.6%	Not measured	Only Gemini 3.8 Flash measured
WeirdML	84.8%	60.3%	Gemini 3.8 Flash
ALE-Bench	1269.7	1188.6	Gemini 3.8 Flash
LMArena Text: coding	1508	1438	Gemini 3.8 Flash
LMArena Text: software and IT	1507	1436	Gemini 3.8 Flash
LMArena WebDev: React	1577	1386	Gemini 3.8 Flash
LMArena WebDev: HTML	1616	1419	Gemini 3.8 Flash
LMArena WebDev: from an image	1593	Not measured	Only Gemini 3.8 Flash measured
Neither model has a result on the other 12 boards here

IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20

Intelligence benchmarks for Gemini 3.8 Flash and GPT-5.4 Mini
Benchmark	Gemini 3.8 Flash	GPT-5.4 Mini	Leader
AA Intelligence Index	40.9	24.1	Gemini 3.8 Flash
Epoch Capabilities Index	157.4	148.7	Gemini 3.8 Flash

Agentic workLike-for-likePublic boards, shown as published, kept out of the index50

Agentic work benchmarks for Gemini 3.8 Flash and GPT-5.4 Mini
Benchmark	Gemini 3.8 Flash	GPT-5.4 Mini	Leader
AA Agentic Index	40.2	17.9	Gemini 3.8 Flash
Design Arena: agents building web apps	1238	Not measured	Only Gemini 3.8 Flash measured
Design Arena: agents building full-stack apps	1244	Not measured	Only Gemini 3.8 Flash measured
Design Arena: agents building mobile apps	1236	Not measured	Only Gemini 3.8 Flash measured
Design Arena: agents building Android apps	1078	Not measured	Only Gemini 3.8 Flash measured
Design Arena: agents building Godot games	1273	Not measured	Only Gemini 3.8 Flash measured
Design Arena: PowerPoint slides	1178	Not measured	Only Gemini 3.8 Flash measured
Design Arena: spreadsheets	1052	Not measured	Only Gemini 3.8 Flash measured
LiveBench research	79.1%	Not measured	Only Gemini 3.8 Flash measured
LiveBench browser	64.0%	Not measured	Only Gemini 3.8 Flash measured
LiveBench long agentic	30.1%	Not measured	Only Gemini 3.8 Flash measured
SREBench (Vals AI)	11.1%	Not measured	Only Gemini 3.8 Flash measured
Finance Agent (Vals AI)	61.4%	45.4%	Gemini 3.8 Flash
Tax Agent Bench (Vals AI)	32.1%	8.8%	Gemini 3.8 Flash
Legal Research Bench (Vals AI)	38.9%	12.5%	Gemini 3.8 Flash
Harvey's Legal Agent Benchmark (Vals AI)	12.1%	Not measured	Only Gemini 3.8 Flash measured
Excel Modeling Benchmark (Vals AI)	72.2%	45.4%	Gemini 3.8 Flash
BioMysteryBench (Vals AI)	62.2%	Not measured	Only Gemini 3.8 Flash measured
Terminal-Bench-Science (Vals AI)	8.6%	Not measured	Only Gemini 3.8 Flash measured
Vals Science Index	35.8%	Not measured	Only Gemini 3.8 Flash measured
Time Horizon Index (Vals AI)	18.8%	Not measured	Only Gemini 3.8 Flash measured
CUA-bench (Vals AI)	4.2%	Not measured	Only Gemini 3.8 Flash measured
τ²-Bench Telecom	Not measured	83.3%	Only GPT-5.4 Mini measured
APEX-Agents	64.3%	Not measured	Only Gemini 3.8 Flash measured
Remote Labor Index	5.8%	Not measured	Only Gemini 3.8 Flash measured
DeepResearch Bench	Not measured	36.3%	Only GPT-5.4 Mini measured
Vending-Bench 2	$5,094	Not measured	Only Gemini 3.8 Flash measured
Neither model has a result on the other 12 boards here

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

Reasoning benchmarks for Gemini 3.8 Flash and GPT-5.4 Mini
Benchmark	Gemini 3.8 Flash	GPT-5.4 Mini	Leader
GPQA Diamond	94.4%	83.1%	Gemini 3.8 Flash
LiveBench reasoning	89.3%	Not measured	Only Gemini 3.8 Flash measured
MysteryMechanism (Vals AI)	36.5%	Not measured	Only Gemini 3.8 Flash measured
MMMU Pro (Vals AI)	89.1%	79.3%	Gemini 3.8 Flash
GPQA Diamond (Artificial Analysis run)	95.3%	87.5%	Gemini 3.8 Flash
Humanity's Last Exam (Artificial Analysis run)	47.8%	28.1%	Gemini 3.8 Flash
GPQA Diamond (Epoch AI run)	95.4%	86.9%	Gemini 3.8 Flash
ARC-AGI	98.5%	63.7%	Gemini 3.8 Flash
ARC-AGI-2	89.2%	18.9%	Gemini 3.8 Flash
Chess puzzles	58.0%	23.0%	Gemini 3.8 Flash
Mystery game puzzles	47.0%	11.0%	Gemini 3.8 Flash
LMArena Text: hard prompts	1509	1424	Gemini 3.8 Flash
LMArena Text: expert	1526	1435	Gemini 3.8 Flash
LMArena Text: hard prompts in English	1504	1420	Gemini 3.8 Flash
LMArena Vision: diagrams	1345	1266	Gemini 3.8 Flash
LMArena Vision: homework	1351	1285	Gemini 3.8 Flash
Neither model has a result on the other 5 boards here

MathLike-for-likePublic boards, shown as published, kept out of the index60

Math benchmarks for Gemini 3.8 Flash and GPT-5.4 Mini
Benchmark	Gemini 3.8 Flash	GPT-5.4 Mini	Leader
AIME	Not measured	95.6%	Only GPT-5.4 Mini measured
OTIS Mock AIME	98.9%	88.9%	Gemini 3.8 Flash
FrontierMath, tiers 1 to 3	68.4%	51.2%	Gemini 3.8 Flash
FrontierMath, tier 4	22.0%	9.8%	Gemini 3.8 Flash
ProofBench	48.0%	21.0%	Gemini 3.8 Flash
LMArena Text: math	1532	1418	Gemini 3.8 Flash
LMArena Text: mathematical work	1519	1429	Gemini 3.8 Flash
Neither model has a result on the other 6 boards here

KnowledgeLike-for-likePublic boards, shown as published, kept out of the index80

Knowledge benchmarks for Gemini 3.8 Flash and GPT-5.4 Mini
Benchmark	Gemini 3.8 Flash	GPT-5.4 Mini	Leader
MMLU Pro	90.2%	84.5%	Gemini 3.8 Flash
LegalBench (Vals AI)	87.0%	Not measured	Only Gemini 3.8 Flash measured
CaseLaw (Vals AI)	Not measured	51.7%	Only GPT-5.4 Mini measured
CorpFin (Vals AI)	Not measured	60.9%	Only GPT-5.4 Mini measured
TaxEval (Vals AI)	74.5%	71.2%	Gemini 3.8 Flash
MortgageTax (Vals AI)	65.3%	63.5%	Gemini 3.8 Flash
MedCode (Vals AI)	48.1%	Not measured	Only Gemini 3.8 Flash measured
SimpleQA Verified	69.7%	29.4%	Gemini 3.8 Flash
LMArena Text: science	1523	1417	Gemini 3.8 Flash
LMArena Text: medicine and healthcare	1508	1395	Gemini 3.8 Flash
LMArena Text: legal and government	1497	1414	Gemini 3.8 Flash
LMArena Text: business and finance	1479	1418	Gemini 3.8 Flash
Neither model has a result on the other 5 boards here

Web designDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared

Web design benchmarks for Gemini 3.8 Flash and GPT-5.4 Mini
Benchmark	Gemini 3.8 Flash	GPT-5.4 Mini	Leader
Design Arena: websites	1301	Not measured	Only Gemini 3.8 Flash measured
Design Arena: UI components	1318	Not measured	Only Gemini 3.8 Flash measured
Design Arena: game dev	1305	Not measured	Only Gemini 3.8 Flash measured
Design Arena: data viz	1269	Not measured	Only Gemini 3.8 Flash measured
Design Arena: 3D	1295	Not measured	Only Gemini 3.8 Flash measured
Design Arena: all code categories	1304	Not measured	Only Gemini 3.8 Flash measured
Design Arena: SVG	1295	Not measured	Only Gemini 3.8 Flash measured
Design Arena: ASCII art	1264	Not measured	Only Gemini 3.8 Flash measured
LiveBench design	72.7%	Not measured	Only Gemini 3.8 Flash measured

GeneralLike-for-likePublic boards, shown as published, kept out of the index261

General benchmarks for Gemini 3.8 Flash and GPT-5.4 Mini
Benchmark	Gemini 3.8 Flash	GPT-5.4 Mini	Leader
Vals Index	56.0%	Not measured	Only Gemini 3.8 Flash measured
LiveBench data analysis	54.0%	Not measured	Only Gemini 3.8 Flash measured
Public Benefits Bench (Vals AI)	65.3%	Not measured	Only Gemini 3.8 Flash measured
SAGE (Vals AI)	35.1%	50.8%	GPT-5.4 Mini
MedScribe (Vals AI)	84.5%	Not measured	Only Gemini 3.8 Flash measured
Vals Multimodal Index	Not measured	54.2%	Only GPT-5.4 Mini measured
IFBench	Not measured	73.3%	Only GPT-5.4 Mini measured
Long context reasoning (AA-LCR)	84.0%	77.0%	Gemini 3.8 Flash
DTBench	95.7%	80.0%	Gemini 3.8 Flash
LMCA	52.9%	40.8%	Gemini 3.8 Flash
Surface Evolver Bench	76.9%	Not measured	Only Gemini 3.8 Flash measured
Furniture assembly	31.7%	Not measured	Only Gemini 3.8 Flash measured
LMArena Text	1499	1412	Gemini 3.8 Flash
LMArena Text: instruction following	1492	1405	Gemini 3.8 Flash
LMArena Text: creative writing	1488	1370	Gemini 3.8 Flash
LMArena Vision	1315	1245	Gemini 3.8 Flash
LMArena Text: English	1498	1412	Gemini 3.8 Flash
LMArena Text: non-English	1491	1405	Gemini 3.8 Flash
LMArena Text: Chinese	1553	1446	Gemini 3.8 Flash
LMArena Text: German	1501	1408	Gemini 3.8 Flash
LMArena Text: Japanese	1507	1375	Gemini 3.8 Flash
LMArena Text: Korean	1464	1370	Gemini 3.8 Flash
LMArena Text: French	1496	1441	Gemini 3.8 Flash
LMArena Text: Spanish	1487	1405	Gemini 3.8 Flash
LMArena Text: Russian	1514	1417	Gemini 3.8 Flash
LMArena Text: Polish	1497	1415	Gemini 3.8 Flash
LMArena Text: multi-turn	1503	1429	Gemini 3.8 Flash
LMArena Text: longer queries	1507	1408	Gemini 3.8 Flash
LMArena Text: writing and language	1494	1393	Gemini 3.8 Flash
LMArena Text: entertainment and media	1480	1373	Gemini 3.8 Flash
LMArena Vision: English	1318	1244	Gemini 3.8 Flash
LMArena Vision: Chinese	1416	1286	Gemini 3.8 Flash
LMArena Vision: reading text	1333	1253	Gemini 3.8 Flash
LMArena Vision: humor	1321	1235	Gemini 3.8 Flash
LMArena Vision: recognizing things	Not measured	1218	Only GPT-5.4 Mini measured
LMArena Vision: creative writing	1299	1222	Gemini 3.8 Flash
Neither model has a result on the other 10 boards here

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

Image generation benchmarks for Gemini 3.8 Flash and GPT-5.4 Mini
Benchmark	Gemini 3.8 Flash	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 3.8 Flash$0.0029Fits in one request

GPT-5.4 Mini$0.0030Fits in one request

Gemini 3.8 Flash costs less

Repository review

50K input + 3K output tokens

Gemini 3.8 Flash$0.054Fits 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 3.8 Flash$0.206Fits 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 3.8 Flash and GPT-5.4 Mini
Specification	Google Gemini 3.8 Flash	OpenAI GPT-5.4 Mini
Maker	Google	OpenAI
Weights	No public weights listed	No public weights listed
Released	September 2, 2026	March 17, 2026
Context window	1.05M	400K
Input $/Mtok	$0.825	$0.75
Output $/Mtok	$4.125	$4.50
Coding index	70.5	28.2
Independent measurements behind it	2	1
Cost per solved task	$2.74	$0.70
Source	OpenRouter listing	OpenRouter listing

Questions

Is Gemini 3.8 Flash better than GPT-5.4 Mini for coding?

Pick Gemini 3.8 Flash for coding: it scores 70.5 on the Vibe Coding Index against 28.2 for GPT-5.4 Mini. Pick GPT-5.4 Mini when a solved task costs $0.70 against $2.74, or when the benchmark that matters is SAGE (Vals AI), where it leads.

Which is cheaper, Gemini 3.8 Flash or GPT-5.4 Mini?

Gemini 3.8 Flash costs $0.825 per million input tokens and $4.125 per million output tokens; GPT-5.4 Mini costs $0.75 and $4.50. Per solved SWE-bench Verified task, Gemini 3.8 Flash costs $2.74 and GPT-5.4 Mini $0.70.

Which has the bigger context window, Gemini 3.8 Flash or GPT-5.4 Mini?

Gemini 3.8 Flash, with 1.05M tokens against 400K.

How many benchmarks is the Gemini 3.8 Flash vs GPT-5.4 Mini comparison based on?

79 benchmarks have a result for both models as of October 21, 2026. Gemini 3.8 Flash's coding index rests on 2 independent benchmarks and GPT-5.4 Mini's on 1. Where only one model has a result, the page says so instead of naming a winner.

Decision reading

Which one for your work

Coding

Intelligence

Agentic work

Reasoning

Math

Knowledge

Web design

General

Long documents

Everyday cost

Cost per solved task