Skip to main content

OpenAIGoogleLLM matchup

GPT-5.4 minivs.Gemini 3.6 Flash

Which one is better?

Gemini 3.6 Flash performs better than GPT-5.4 mini and is cheaper: GPT-5.4 mini costs 1.2 times as much for output and about the same for input.

Gemini 3.6 Flash ahead
IntelligenceOverall index, 100 points = average
75.1

GPT-5.4 mini

Rank 62

97.2

Gemini 3.6 Flash

Rank 38

about as fast
SpeedTokens per second
97

GPT-5.4 mini

103

Gemini 3.6 Flash

about the same price
Price$ per 1M tokens
$1.69

GPT-5.4 mini

$1.50

Gemini 3.6 Flash

No clear advantage for GPT-5.4 mini.

Choose Gemini 3.6 Flash for

MultimodalFinanceCodingGeneral

Where is the difference?

Strengths at a glance

GPT-5.4 miniGemini 3.6 FlashMedian of all ranked models

809010011070CodingGemini 3.6FlashGeneralGemini 3.6FlashMultimodalGemini 3.6FlashFinanceGemini 3.6Flash
CodingGemini 3.6 Flash ahead
GPT-5.4 mini75.7Rank 71
Gemini 3.6 Flash91.3Rank 52
Median of ranked models87.5

95 % range: GPT-5.4 mini 70.9 to 80.5, Gemini 3.6 Flash 86.8 to 95.7.

AreaGPT-5.4 miniGemini 3.6 Flash

The same values and verdicts as the bars below. In the close-up the net starts at 70 points, just below the weaker model's lowest value; the reference group average is 100. Not in the net because a model has no own value there or the data are too thin: Reasoning, Mathematics, Knowledge, Agents, Legal, Health.

Gemini 3.6 Flash is ahead in 4 of 10 areas, GPT-5.4 mini in none.

too little data: 6Gemini 3.6 Flash ahead: 4

Areas in the overall index
MultimodalGemini 3.6 Flash +2875.1 to 103.2
CodingGemini 3.6 Flash +1675.7 to 91.3
GeneralGemini 3.6 Flash +1179.3 to 90.1
Knowledgetoo little data73.8 to 107.4
Reasoningtoo little data72.9 to 103.2
Agentstoo little data78.7 to 93.0
Mathematicsonly Gemini 3.6 Flash has a score
Specialist fields
FinanceGemini 3.6 Flash +2175.1 to 96.0
Legaltoo little data71.3 to 93.3
Healthonly Gemini 3.6 Flash has a score

Bar length shows the gap in index points (full width 15 points, one standard deviation of the reference group). Solid means clearly ahead, hatched not certain yet, a thin grey bar level.

Show 2 more areas that do not count toward the overall index
Cybersecurityonly Gemini 3.6 Flash has a score
Productivityonly Gemini 3.6 Flash has a score

Bar length shows the gap in index points (full width 15 points, one standard deviation of the reference group). Solid means clearly ahead, hatched not certain yet, a thin grey bar level.

Which model for which task?

Everyday tasks, translated from the area values above. Each row names the values it rests on.

Writing and debugging codeGemini 3.6 FlashCoding 75.7 to 91.3
Maths and data analysisopenMathematics without a score for GPT-5.4 mini, Reasoning 72.9 to 103.2 (too little data)
Facts and researchopenKnowledge 73.8 to 107.4 (too little data)
Agents and workflowsopenAgents 78.7 to 93.0 (too little data)
Fast chat repliesabout the same97 to 103 tokens per second
Security analysisopenCybersecurity without a score for GPT-5.4 mini
Many requests on a small budgetabout the same$1.69 to $1.50 per 1M tokens
Finance, legal and medical textsGemini 3.6 FlashFinance 75.1 to 96.0, Legal 71.3 to 93.3 (too little data), Health without a score for GPT-5.4 mini
Images, screenshots and PDFsGemini 3.6 FlashMultimodal 75.1 to 103.2

GPT-5.4 mini vs. Gemini 3.6 Flash in our own test

The same prompt for both models. We show the latest attempt without fixes; it does not count toward the overall index.

Pelican on a bicycle

Prompt

Generate an SVG of a pelican riding a bicycle

Task origin: Simon Willison

GPT-5.4 mini

GPT-5.4 mini: Pelican on a bicycle
A community classic for free-form SVG drawing.

Oct 2, 2026 · 14 s · $0.01

Test details
Run date
Oct 2, 2026
API provider
openrouter
Requested API model
openai/gpt-5.4-mini
Reasoning setting
high
Token limit including reasoning
8,192 tokens
Output tokens
3,142 tokens
Cost of the attempt
$0.0142
Response time
13.5 s
API model reported in response
openai/gpt-5.4-mini
Pinned endpoint
OpenAI | openai/gpt-5.4-mini-20260317
Temperature
Provider default
Test protocol
community-visual-tests-v1
Technical checks
Passed, not a quality rating

Visually reviewed. This individual test does not establish overall model quality.

Earlier attempts (2)

  • Oct 1, 2026API request failedReasoning setting: high
  • Sep 7, 2026API request failedReasoning setting: high

Gemini 3.6 Flash

The response reached the token limit. No complete recording is available.

Oct 5, 2026 · 40 s · $0.03

Not yet visually reviewed. A successful recording does not confirm correct physics or full compliance with the prompt.

Test details
Run date
Oct 5, 2026
API provider
openrouter
Requested API model
google/gemini-3.6-flash
Reasoning setting
high
Token limit including reasoning
8,192 tokens
Output tokens
8,188 tokens
Cost of the attempt
$0.0307
Response time
39.6 s
API model reported in response
google/gemini-3.6-flash
Pinned endpoint
Google AI Studio | google/gemini-3.6-flash-20260721
Temperature
Provider default
Test protocol
community-visual-tests-v1
Technical checks
Failed

Earlier attempts (3)

  • Oct 2, 2026API request failedReasoning setting: high
  • Oct 1, 2026API request failedReasoning setting: high
  • Sep 7, 2026API request failedReasoning setting: high
SVG short test

SVG short test

One SVG task with the same fixed settings for every model, without hidden thinking.

Prompt

Return only one standalone SVG of a pelican riding a bicycle. Use viewBox="0 0 800 600", simple shapes, two clearly visible wheels and a recognizable pelican with a long beak. At most 30 SVG elements and 1800 characters. No Markdown, explanations, comments, scripts, animation, CSS or external resources.

GPT-5.4 mini

Unavailable in this round

Gemini 3.6 Flash

Unavailable in this round

GPT-5.4 mini and Gemini 3.6 Flash in the overall index

Every model with a place in the overall index, both models of this matchup highlighted. You can add or hide other models.

Overall index (Gradually Meta-Score v6)

20 of 95 models

Claude Fable 5.2max130.9
Gemini 4 Carbonhigh127.0
Claude Opus 5.5max125.7
Claude Fable 5.1max124.1
Claude Sonnet 5.5max121.9
Gemini 4 Argonhigh121.2
GPT-6 Astramax119.6
Muse Wonder Fullmax118.4
GPT-6.1 Solmax117.5
Claude Opus 5max117.3
Muse Wondermax113.7
Claude Fable 5max112.8
Kimi K3.1 Promax112.6
Muse Ember 1.0max110.5
GPT-5.6 Solmax109.3
GPT-6 Solmax108.4
Gemini 3.7 Flashhigh107.7
DeepSeek V4.1 Flash 1017max107.1
Gemini 3.6 Flashhigh97.2
GPT-5.4 minixhigh75.1

All data side by side

The better value is bold. For the overall index only when the gap is clear.

MetricGPT-5.4 miniGemini 3.6 Flash
Intelligence
Overall indexpoints, 100 = reference group average, higher is better75.197.2
RankRank 62 of 95Rank 38 of 95
Price per 1M tokens
Inputwhat you send$0.75$0.75
Outputwhat the model writes$4.50$3.75
Speed
Tokens per second97103
Technical
Context windowhow much text the model reads at once400,000 tokens≈ 600 A4 pages1.05 M tokens≈ 1,570 A4 pages
Knowledge cutoffAug 31, 2025March 2026
ReleasedMar 17, 2026Jul 21, 2026
AvailabilityActiveActive
Open weightsnono

Prices without caching or batch discounts · Page count as a rule of thumb from Artificial Analysis

Is there a better choice?

Successor of Gemini 3.6 FlashGemini 3.7 Flash

Overall index 107.7, rank 17No API price in our data yet

GPT-5.4 mini vs. Gemini 3.7 Flash
Cheaper than Gemini 3.6 FlashMuse Ember 1.0

Overall index 110.5, rank 14$0.10 input and $0.50 output per 1M tokens

View profile
Best model in the overall indexClaude Fable 5.2

Overall index 130.9, rank 1$8 input and $40 output per 1M tokens

Shared benchmarks

Single results from the same benchmark version, task and metric. A value is bold only with the same test setup and a clear gap.

A: GPT-5.4 miniB: Gemini 3.6 Flash

Code MigrationOverall · higher is betterTest setup not documented as identicalGPT-5.4 mini: 12.9%Gemini 3.6 Flash: 30.9%Vals AIAs of 10/29/2026
CorpFin v2Overall · higher is betterTest setup not documented as identicalGPT-5.4 mini: 60.9%Gemini 3.6 Flash: 63.3%Vals AIAs of 08/12/2026
EMBOverall · higher is betterTest setup not documented as identicalGPT-5.4 mini: 45.4%Gemini 3.6 Flash: 65.4%Vals AIAs of 10/20/2026
Finance Agent (v2)Overall · higher is betterTest setup not documented as identicalGPT-5.4 mini: 45.4%Gemini 3.6 Flash: 56.3%Vals AIAs of 10/29/2026
GPQA DiamondOverall · higher is betterTest setup not documented as identicalGPT-5.4 mini: 83.1%Gemini 3.6 Flash: 93.4%Vals AIAs of 09/01/2026
Legal Research BenchOverall · All-pass · higher is betterTest setup not documented as identicalGPT-5.4 mini: 12.5%Gemini 3.6 Flash: 25.0%Vals AIAs of 11/05/2026
LiveCodeBenchOverall · higher is betterTest setup not documented as identicalGPT-5.4 mini: 81.5%Gemini 3.6 Flash: 88.1%Vals AIAs of 09/01/2026
LMArena Code Arena WebDevOverall · higher is betterGPT-5.4 mini: 1,398Gemini 3.6 Flash: 1,538LMArenaAs of 11/15/2026
LMArena Text, Style ControlOverall · higher is betterGPT-5.4 mini: 1,447Gemini 3.6 Flash: 1,483LMArenaAs of 11/11/2026
LMArena Vision, Style ControlOverall · higher is betterGPT-5.4 mini: 1,250Gemini 3.6 Flash: 1,280LMArenaAs of 11/09/2026
Show 54 more benchmarks
MMLU ProOverall · higher is betterTest setup not documented as identicalGPT-5.4 mini: 84.6%Gemini 3.6 Flash: 89.3%Vals AIAs of 09/01/2026
MMMU ProOverall · higher is betterTest setup not documented as identicalGPT-5.4 mini: 79.2%Gemini 3.6 Flash: 88.4%Vals AIAs of 09/01/2026
MortgageTaxOverall · higher is betterTest setup not documented as identicalGPT-5.4 mini: 63.5%Gemini 3.6 Flash: 67.6%Vals AIAs of 09/01/2026
ProgramBenchOverall · higher is betterTest setup not documented as identicalGPT-5.4 mini: 0%Gemini 3.6 Flash: 0%Vals AIAs of 11/05/2026
SWE-bench VerifiedOverall · higher is betterTest setup not documented as identicalGPT-5.4 mini: 73.0%Gemini 3.6 Flash: 79.6%Vals AIAs of 09/01/2026
Tax Agent BenchOverall · higher is betterTest setup not documented as identicalGPT-5.4 mini: 8.8%Gemini 3.6 Flash: 18.0%Vals AIAs of 11/05/2026
TaxEval v2Overall · higher is betterTest setup not documented as identicalGPT-5.4 mini: 71.2%Gemini 3.6 Flash: 74.9%Vals AIAs of 09/01/2026
Vals Multimodal IndexOverall · higher is betterTest setup not documented as identicalGPT-5.4 mini: 54.2%Gemini 3.6 Flash: 65.1%Vals AIAs of 08/11/2026
Vibe Code Bench v1.1Overall · higher is betterTest setup not documented as identicalGPT-5.4 mini: 48%Gemini 3.6 Flash: 64%Vals AIAs of 11/05/2026
Code MigrationCLI · higher is betterTest setup not documented as identicalGPT-5.4 mini: 8.2%Gemini 3.6 Flash: 19.3%Vals AIAs of 10/29/2026
CorpFin v2Exact Pages · higher is betterTest setup not documented as identicalGPT-5.4 mini: 61.5%Gemini 3.6 Flash: 61.1%Vals AIAs of 08/12/2026
EMBComps · higher is betterTest setup not documented as identicalGPT-5.4 mini: 40.5%Gemini 3.6 Flash: 70.0%Vals AIAs of 10/20/2026
Finance Agent (v2)Adjustments · higher is betterTest setup not documented as identicalGPT-5.4 mini: 45.4%Gemini 3.6 Flash: 53.6%Vals AIAs of 10/29/2026
GPQA DiamondFew-Shot CoT · higher is betterTest setup not documented as identicalGPT-5.4 mini: 84.8%Gemini 3.6 Flash: 92.4%Vals AIAs of 09/01/2026
Legal Research BenchAdministrative / Regulatory · All-pass · higher is betterTest setup not documented as identicalGPT-5.4 mini: 15.2%Gemini 3.6 Flash: 31.8%Vals AIAs of 11/05/2026
LiveCodeBenchEasy · higher is betterTest setup not documented as identicalGPT-5.4 mini: 97.8%Gemini 3.6 Flash: 99.1%Vals AIAs of 09/01/2026
LMArena Code Arena WebDevHTML development · higher is betterGPT-5.4 mini: 1,420Gemini 3.6 Flash: 1,547LMArenaAs of 11/15/2026
LMArena Text, Style ControlBusiness, management and finance · higher is betterGPT-5.4 mini: 1,459Gemini 3.6 Flash: 1,474LMArenaAs of 11/11/2026
LMArena Vision, Style ControlChinese · higher is betterGPT-5.4 mini: 1,285Gemini 3.6 Flash: 1,330LMArenaAs of 11/09/2026
MMLU ProBiology · higher is betterTest setup not documented as identicalGPT-5.4 mini: 91.4%Gemini 3.6 Flash: 94.7%Vals AIAs of 09/01/2026
MortgageTaxNumerical Extraction · higher is betterTest setup not documented as identicalGPT-5.4 mini: 79.4%Gemini 3.6 Flash: 76.8%Vals AIAs of 09/01/2026
ProgramBenchAlmost Resolved · higher is betterTest setup not documented as identicalGPT-5.4 mini: 3.0%Gemini 3.6 Flash: 2.5%Vals AIAs of 11/05/2026
SWE-bench Verified<15 min fix · higher is betterTest setup not documented as identicalGPT-5.4 mini: 85.6%Gemini 3.6 Flash: 87.1%Vals AIAs of 09/01/2026
Tax Agent BenchControversy & Precedence Analysis · higher is betterTest setup not documented as identicalGPT-5.4 mini: 3.3%Gemini 3.6 Flash: 3.3%Vals AIAs of 11/05/2026
TaxEval v2Correctness · higher is betterTest setup not documented as identicalGPT-5.4 mini: 63.0%Gemini 3.6 Flash: 63.5%Vals AIAs of 09/01/2026
Vals Multimodal IndexCorpFin v2 · higher is betterTest setup not documented as identicalGPT-5.4 mini: 60.3%Gemini 3.6 Flash: 63.5%Vals AIAs of 08/11/2026
Code MigrationCOBOL · higher is betterTest setup not documented as identicalGPT-5.4 mini: 27.1%Gemini 3.6 Flash: 65.7%Vals AIAs of 10/29/2026
CorpFin v2Max Fitting Context · higher is betterTest setup not documented as identicalGPT-5.4 mini: 61.0%Gemini 3.6 Flash: 65.4%Vals AIAs of 08/12/2026
EMBDataroom · higher is betterTest setup not documented as identicalGPT-5.4 mini: 48.3%Gemini 3.6 Flash: 73.0%Vals AIAs of 10/20/2026
Finance Agent (v2)All-Pass · higher is betterTest setup not documented as identicalGPT-5.4 mini: 32.4%Gemini 3.6 Flash: 44.6%Vals AIAs of 10/29/2026
GPQA DiamondZero-Shot CoT · higher is betterTest setup not documented as identicalGPT-5.4 mini: 81.3%Gemini 3.6 Flash: 94.4%Vals AIAs of 09/01/2026
Legal Research BenchAdministrative / Regulatory · Weighted partial credit (weighted pass) · higher is betterTest setup not documented as identicalGPT-5.4 mini: 69.7%Gemini 3.6 Flash: 83.5%Vals AIAs of 11/05/2026
LiveCodeBenchHard · higher is betterTest setup not documented as identicalGPT-5.4 mini: 61.7%Gemini 3.6 Flash: 74.6%Vals AIAs of 09/01/2026
LMArena Code Arena WebDevReact development · higher is betterGPT-5.4 mini: 1,386Gemini 3.6 Flash: 1,526LMArenaAs of 11/15/2026
LMArena Text, Style ControlChinese · higher is betterGPT-5.4 mini: 1,473Gemini 3.6 Flash: 1,532LMArenaAs of 11/11/2026
LMArena Vision, Style ControlCreative writing with images · higher is betterGPT-5.4 mini: 1,225Gemini 3.6 Flash: 1,253LMArenaAs of 11/09/2026
MMLU ProBusiness · higher is betterTest setup not documented as identicalGPT-5.4 mini: 89.7%Gemini 3.6 Flash: 92.8%Vals AIAs of 09/01/2026
MortgageTaxSemantic Extraction · higher is betterTest setup not documented as identicalGPT-5.4 mini: 47.6%Gemini 3.6 Flash: 58.4%Vals AIAs of 09/01/2026
ProgramBenchFully Resolved · higher is betterTest setup not documented as identicalGPT-5.4 mini: 0%Gemini 3.6 Flash: 0%Vals AIAs of 11/05/2026
SWE-bench Verified>4 hours · higher is betterTest setup not documented as identicalGPT-5.4 mini: 0.0%Gemini 3.6 Flash: 33.3%Vals AIAs of 09/01/2026
Tax Agent BenchControversy & Precedence Analysis (weighted pass) · higher is betterTest setup not documented as identicalGPT-5.4 mini: 32.2%Gemini 3.6 Flash: 37.4%Vals AIAs of 11/05/2026
TaxEval v2Stepwise Reasoning · higher is betterTest setup not documented as identicalGPT-5.4 mini: 79.4%Gemini 3.6 Flash: 86.2%Vals AIAs of 09/01/2026
Vals Multimodal IndexFinance Agent v2 · higher is betterTest setup not documented as identicalGPT-5.4 mini: 45.4%Gemini 3.6 Flash: 55.3%Vals AIAs of 08/11/2026
Code MigrationCode Quality · higher is betterTest setup not documented as identicalGPT-5.4 mini: 3.053 / 5Gemini 3.6 Flash: 3.299 / 5Vals AIAs of 10/29/2026
CorpFin v2Shared Max Context · higher is betterTest setup not documented as identicalGPT-5.4 mini: 60.3%Gemini 3.6 Flash: 63.5%Vals AIAs of 08/12/2026
EMBDCF · higher is betterTest setup not documented as identicalGPT-5.4 mini: 40.6%Gemini 3.6 Flash: 59.4%Vals AIAs of 10/20/2026
Finance Agent (v2)Comparables · higher is betterTest setup not documented as identicalGPT-5.4 mini: 40.3%Gemini 3.6 Flash: 47.8%Vals AIAs of 10/29/2026
Legal Research BenchBusiness & Commercial · All-pass · higher is betterTest setup not documented as identicalGPT-5.4 mini: 11.6%Gemini 3.6 Flash: 23.3%Vals AIAs of 11/05/2026
LiveCodeBenchMedium · higher is betterTest setup not documented as identicalGPT-5.4 mini: 84.9%Gemini 3.6 Flash: 90.6%Vals AIAs of 09/01/2026
LMArena Code Arena WebDevWeb development · higher is betterGPT-5.4 mini: 1,398Gemini 3.6 Flash: 1,538LMArenaAs of 11/15/2026
LMArena Text, Style ControlCoding · higher is betterGPT-5.4 mini: 1,495Gemini 3.6 Flash: 1,518LMArenaAs of 11/11/2026
LMArena Vision, Style ControlDiagram understanding · higher is betterGPT-5.4 mini: 1,283Gemini 3.6 Flash: 1,312LMArenaAs of 11/09/2026
MMLU ProChemistry · higher is betterTest setup not documented as identicalGPT-5.4 mini: 89.1%Gemini 3.6 Flash: 92.3%Vals AIAs of 09/01/2026
ProgramBenchRaw Pass Rate · higher is betterTest setup not documented as identicalGPT-5.4 mini: 54.4%Gemini 3.6 Flash: 59.9%Vals AIAs of 11/05/2026

More comparisons

Compare GPT-5.4 mini and Gemini 3.6 Flash with the models people compare them with most often.

Compare another matchup

The most popular comparisons

  1. 1GPT-6 Luna vs. GPT-5.4 mini
  2. 2GPT-5.6 Luna vs. GPT-5.4 mini
  3. 3Claude Sonnet 5.5 vs. Gemini 3.6 Flash
  4. 4Gemini 3.8 Flash vs. Gemini 3.6 Flash
  5. 5Gemini 3.6 Flash vs. DeepSeek-V4.1-Flash
  6. 6GPT-6 Luna vs. Gemini 3.6 Flash
  7. 7Gemini 3.6 Flash vs. Gemini 3.1 Pro Preview
  8. 8Claude Opus 5.5 vs. Gemini 3.6 Flash
  9. 9Claude Haiku 5.5 vs. GPT-5.4 mini
Show all 24 comparisons
  1. 10GPT-5.4 mini vs. Gemini 3.8 Flash
  2. 11Claude Haiku 5.5 vs. Gemini 3.6 Flash
  3. 12GPT-5.4 mini vs. Qwen 3.8 27B
  4. 13GPT-5.4 mini vs. DeepSeek-V4-Flash
  5. 14Claude Sonnet 5.5 vs. GPT-5.4 mini
  6. 15Gemini 3.6 Flash vs. Qwen 3.8 27B
  7. 16Gemini 3.6 Flash vs. DeepSeek V4.1 Flash 1017
  8. 17GPT-6 Sol vs. Gemini 3.6 Flash
  9. 18Claude Opus 4.6 vs. Gemini 3.6 Flash
  10. 19GPT-6.1 Sol vs. GPT-5.4 mini
  11. 20Gemini 4 Argon vs. Gemini 3.6 Flash
  12. 21GPT-6.1 Terra vs. GPT-5.4 mini
  13. 22Gemini 4 Carbon vs. Gemini 3.6 Flash
  14. 23GPT-6.1 Terra vs. Gemini 3.6 Flash
  15. 24GPT-6.1 Sol vs. Gemini 3.6 Flash