Skip to main content

OpenAIGoogleLLM matchup

GPT-5.4vs.Gemini 3.5 Flash

Which one is better?

Gemini 3.5 Flash performs better than GPT-5.4.

Gemini 3.5 Flash ahead
IntelligenceOverall index, 100 points = average
86.4

GPT-5.4

Rank 50

96.4

Gemini 3.5 Flash

Rank 39

Gemini 3.5 Flash faster
SpeedTokens per second
62

GPT-5.4

102

Gemini 3.5 Flash

Price$ per 1M tokens
$5.63

GPT-5.4

n/a

Gemini 3.5 Flash

Above 272,000 tokens of context, GPT-5.4 costs more: $5 input and $22.50 output per 1M tokens.

No clear advantage for GPT-5.4.

Choose Gemini 3.5 Flash for

HealthMultimodalFinanceAgentsLegal (not certain)Reasoning (not certain)Coding (not certain)

Where is the difference?

Strengths at a glance

GPT-5.4Gemini 3.5 FlashMedian of all ranked models

859510575CodingslightlyGemini 3.5FlashReasoningslightlyGemini 3.5FlashAgentsGemini 3.5FlashMultimodalGemini 3.5FlashFinanceGemini 3.5FlashLegalslightlyGemini 3.5FlashHealthGemini 3.5Flash
CodingGemini 3.5 Flash slightly ahead
GPT-5.485.0Rank 60
Gemini 3.5 Flash89.7Rank 55
Median of ranked models87.5

95 % range: GPT-5.4 75.3 to 94.6, Gemini 3.5 Flash 84.0 to 95.4.

AreaGPT-5.4Gemini 3.5 Flash

The same values and verdicts as the bars below. In the close-up the net starts at 75 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: Mathematics, Knowledge, General.

Gemini 3.5 Flash is ahead in 4 of 10 areas, GPT-5.4 in none.

too little data: 3Gemini 3.5 Flash slightly ahead: 3Gemini 3.5 Flash ahead: 4

Areas in the overall index
MultimodalGemini 3.5 Flash +1588.8 to 104.0
AgentsGemini 3.5 Flash +890.5 to 98.0
Reasoningleaning Gemini 3.5 Flashnot certain · 3 and 4 tests
Codingleaning Gemini 3.5 Flashnot certain · 6 and 8 tests
Knowledgetoo little data87.0 to 107.6
Generaltoo little data86.1 to 85.7
Mathematicsonly Gemini 3.5 Flash has a score
Specialist fields
HealthGemini 3.5 Flash +1980.4 to 99.0
FinanceGemini 3.5 Flash +1285.9 to 98.2
Legalleaning Gemini 3.5 Flashnot certain · 2 tests each

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 1 more areas that do not count toward the overall index
Productivityonly Gemini 3.5 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 codeleaning Gemini 3.5 FlashCoding 85.0 to 89.7
Maths and data analysisleaning Gemini 3.5 FlashMathematics without a score for GPT-5.4, Reasoning 87.9 to 95.2
Facts and researchopenKnowledge 87.0 to 107.6 (too little data)
Agents and workflowsGemini 3.5 FlashAgents 90.5 to 98.0
Fast chat repliesGemini 3.5 Flash62 to 102 tokens per second
Finance, legal and medical textsGemini 3.5 FlashFinance 85.9 to 98.2, Legal 83.9 to 93.2, Health 80.4 to 99.0
Images, screenshots and PDFsGemini 3.5 FlashMultimodal 88.8 to 104.0

GPT-5.4 vs. Gemini 3.5 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

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

Oct 1, 2026 · 117 s · $0.11

Test details
Run date
Oct 1, 2026
API provider
openrouter
Requested API model
openai/gpt-5.4
Reasoning setting
high
Token limit including reasoning
8,192 tokens
Output tokens
7,339 tokens
Cost of the attempt
$0.1101
Response time
116.8 s
API model reported in response
openai/gpt-5.4
Pinned endpoint
OpenAI | openai/gpt-5.4-20260305
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 (1)

  • Sep 7, 2026API request failedReasoning setting: high

Gemini 3.5 Flash

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

Oct 6, 2026 · 32 s · $0.07

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

Test details
Run date
Oct 6, 2026
API provider
openrouter
Requested API model
google/gemini-3.5-flash
Reasoning setting
high
Token limit including reasoning
8,192 tokens
Output tokens
8,188 tokens
Cost of the attempt
$0.0737
Response time
31.7 s
API model reported in response
google/gemini-3.5-flash
Pinned endpoint
Google AI Studio | google/gemini-3.5-flash-20260519
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

Unavailable in this round

Gemini 3.5 Flash

Unavailable in this round

GPT-5.4 and Gemini 3.5 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 3.5 Flashhigh96.4
GPT-5.4xhigh86.4

All data side by side

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

MetricGPT-5.4Gemini 3.5 Flash
Intelligence
Overall indexpoints, 100 = reference group average, higher is better86.496.4
RankRank 50 of 95Rank 39 of 95
Price per 1M tokens
Inputwhat you send$2.50above 272,000 tokens: $5n/a
Outputwhat the model writes$15above 272,000 tokens: $22.50n/a
Cost per task (own tests)average of 2 original-protocol tasks both models passed (SVG short test not included)$0.23$0.12
Speed
Tokens per second62102
Technical
Context windowhow much text the model reads at once1.05 M tokens≈ 1,580 A4 pages1.05 M tokens≈ 1,570 A4 pages
Knowledge cutoffAug 31, 2025n/a
ReleasedMar 5, 2026May 19, 2026
AvailabilityActiveDiscontinued
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 GPT-5.4GPT-5.5

Overall index 101.4, rank 27$5 input and $30 output per 1M tokens

Gemini 3.5 Flash vs. GPT-5.5
Successor of Gemini 3.5 FlashGemini 3.6 Flash

Overall index 97.2, rank 38$0.75 input and $3.75 output per 1M tokens

GPT-5.4 vs. Gemini 3.6 Flash
Best model in the overall indexClaude Fable 5.2

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

View profile

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-5.4B: Gemini 3.5 Flash

Code MigrationOverall · higher is betterTest setup not documented as identicalGPT-5.4: 35.0%Gemini 3.5 Flash: 26.7%Vals AIAs of 10/29/2026
CorpFin v2Overall · higher is betterTest setup not documented as identicalGPT-5.4: 65.3%Gemini 3.5 Flash: 64.7%Vals AIAs of 08/12/2026
GPQA DiamondOverall · higher is betterTest setup not documented as identicalGPT-5.4: 91.7%Gemini 3.5 Flash: 92.7%Vals AIAs of 09/01/2026
LegalBenchOverall · higher is betterTest setup not documented as identicalGPT-5.4: 86.0%Gemini 3.5 Flash: 83.6%Vals AIAs of 10/13/2026
LiveCodeBenchOverall · higher is betterTest setup not documented as identicalGPT-5.4: 84.1%Gemini 3.5 Flash: 87.6%Vals AIAs of 09/01/2026
LMArena Code Arena WebDevImage to WebDev · higher is betterTest setup not documented as identicalGPT-5.4: 1,441Gemini 3.5 Flash: 1,500LMArenaAs of 11/15/2026
LMArena Text, Style ControlOverall · higher is betterGPT-5.4: 1,475Gemini 3.5 Flash: 1,478LMArenaAs of 11/11/2026
LMArena Vision, Style ControlOverall · higher is betterGPT-5.4: 1,282Gemini 3.5 Flash: 1,281LMArenaAs of 11/09/2026
MedCodeOverall · higher is betterTest setup not documented as identicalGPT-5.4: 41.3%Gemini 3.5 Flash: 55.8%Vals AIAs of 10/29/2026
MedScribeOverall · higher is betterTest setup not documented as identicalGPT-5.4: 77.5%Gemini 3.5 Flash: 76.6%Vals AIAs of 10/29/2026
Show 54 more benchmarks
MMLU ProOverall · higher is betterTest setup not documented as identicalGPT-5.4: 87.5%Gemini 3.5 Flash: 89.5%Vals AIAs of 09/01/2026
MMMU ProOverall · higher is betterTest setup not documented as identicalGPT-5.4: 87.5%Gemini 3.5 Flash: 88.3%Vals AIAs of 09/01/2026
MortgageTaxOverall · higher is betterTest setup not documented as identicalGPT-5.4: 68.3%Gemini 3.5 Flash: 68.1%Vals AIAs of 09/01/2026
ProgramBenchOverall · higher is betterTest setup not documented as identicalGPT-5.4: 0%Gemini 3.5 Flash: 0%Vals AIAs of 11/05/2026
SkillsBenchOverall · higher is betterTest setup not documented as identicalGPT-5.4: 51.7%Gemini 3.5 Flash: 52.7%Vals AIAs of 10/29/2026
SWE-bench VerifiedOverall · higher is betterTest setup not documented as identicalGPT-5.4: 78.2%Gemini 3.5 Flash: 78.8%Vals AIAs of 09/01/2026
TaxEval v2Overall · higher is betterTest setup not documented as identicalGPT-5.4: 74.0%Gemini 3.5 Flash: 74.4%Vals AIAs of 09/01/2026
Vibe Code Bench v1.1Overall · higher is betterTest setup not documented as identicalGPT-5.4: 67.4%Gemini 3.5 Flash: 48.7%Vals AIAs of 11/05/2026
Code MigrationCLI · higher is betterTest setup not documented as identicalGPT-5.4: 23.8%Gemini 3.5 Flash: 17.2%Vals AIAs of 10/29/2026
CorpFin v2Exact Pages · higher is betterTest setup not documented as identicalGPT-5.4: 64.1%Gemini 3.5 Flash: 62.8%Vals AIAs of 08/12/2026
GPQA DiamondFew-Shot CoT · higher is betterTest setup not documented as identicalGPT-5.4: 91.4%Gemini 3.5 Flash: 91.4%Vals AIAs of 09/01/2026
LegalBenchConclusion Tasks · higher is betterTest setup not documented as identicalGPT-5.4: 88.9%Gemini 3.5 Flash: 81.9%Vals AIAs of 10/13/2026
LiveCodeBenchEasy · higher is betterTest setup not documented as identicalGPT-5.4: 99.1%Gemini 3.5 Flash: 99.1%Vals AIAs of 09/01/2026
LMArena Text, Style ControlBusiness, management and finance · higher is betterGPT-5.4: 1,482Gemini 3.5 Flash: 1,468LMArenaAs of 11/11/2026
LMArena Vision, Style ControlChinese · higher is betterGPT-5.4: 1,317Gemini 3.5 Flash: 1,341LMArenaAs of 11/09/2026
MMLU ProBiology · higher is betterTest setup not documented as identicalGPT-5.4: 92.9%Gemini 3.5 Flash: 93.9%Vals AIAs of 09/01/2026
MortgageTaxNumerical Extraction · higher is betterTest setup not documented as identicalGPT-5.4: 76.0%Gemini 3.5 Flash: 77.5%Vals AIAs of 09/01/2026
ProgramBenchAlmost Resolved · higher is betterTest setup not documented as identicalGPT-5.4: 7.0%Gemini 3.5 Flash: 1.5%Vals AIAs of 11/05/2026
SkillsBenchNo Skills · higher is betterTest setup not documented as identicalGPT-5.4: 48.9%Gemini 3.5 Flash: 41.0%Vals AIAs of 10/29/2026
SWE-bench Verified<15 min fix · higher is betterTest setup not documented as identicalGPT-5.4: 88.1%Gemini 3.5 Flash: 86.6%Vals AIAs of 09/01/2026
TaxEval v2Correctness · higher is betterTest setup not documented as identicalGPT-5.4: 64.9%Gemini 3.5 Flash: 61.9%Vals AIAs of 09/01/2026
Code MigrationCOBOL · higher is betterTest setup not documented as identicalGPT-5.4: 68.6%Gemini 3.5 Flash: 55.5%Vals AIAs of 10/29/2026
CorpFin v2Max Fitting Context · higher is betterTest setup not documented as identicalGPT-5.4: 64.9%Gemini 3.5 Flash: 66.7%Vals AIAs of 08/12/2026
GPQA DiamondZero-Shot CoT · higher is betterTest setup not documented as identicalGPT-5.4: 91.9%Gemini 3.5 Flash: 93.9%Vals AIAs of 09/01/2026
LegalBenchInterpretation Tasks · higher is betterTest setup not documented as identicalGPT-5.4: 83.9%Gemini 3.5 Flash: 88.7%Vals AIAs of 10/13/2026
LiveCodeBenchHard · higher is betterTest setup not documented as identicalGPT-5.4: 67.7%Gemini 3.5 Flash: 73.1%Vals AIAs of 09/01/2026
LMArena Text, Style ControlChinese · higher is betterGPT-5.4: 1,505Gemini 3.5 Flash: 1,514LMArenaAs of 11/11/2026
LMArena Vision, Style ControlCreative writing with images · higher is betterGPT-5.4: 1,264Gemini 3.5 Flash: 1,272LMArenaAs of 11/09/2026
MMLU ProBusiness · higher is betterTest setup not documented as identicalGPT-5.4: 91.8%Gemini 3.5 Flash: 93.3%Vals AIAs of 09/01/2026
MortgageTaxSemantic Extraction · higher is betterTest setup not documented as identicalGPT-5.4: 60.7%Gemini 3.5 Flash: 58.7%Vals AIAs of 09/01/2026
ProgramBenchFully Resolved · higher is betterTest setup not documented as identicalGPT-5.4: 0%Gemini 3.5 Flash: 0%Vals AIAs of 11/05/2026
SkillsBenchWith Skills · higher is betterTest setup not documented as identicalGPT-5.4: 51.7%Gemini 3.5 Flash: 52.7%Vals AIAs of 10/29/2026
SWE-bench Verified>4 hours · higher is betterTest setup not documented as identicalGPT-5.4: 0.0%Gemini 3.5 Flash: 33.3%Vals AIAs of 09/01/2026
TaxEval v2Stepwise Reasoning · higher is betterTest setup not documented as identicalGPT-5.4: 83.0%Gemini 3.5 Flash: 86.8%Vals AIAs of 09/01/2026
Code MigrationCode Quality · higher is betterTest setup not documented as identicalGPT-5.4: 3.632 / 5Gemini 3.5 Flash: 2.789 / 5Vals AIAs of 10/29/2026
CorpFin v2Shared Max Context · higher is betterTest setup not documented as identicalGPT-5.4: 66.8%Gemini 3.5 Flash: 64.6%Vals AIAs of 08/12/2026
LegalBenchIssue Tasks · higher is betterTest setup not documented as identicalGPT-5.4: 90.5%Gemini 3.5 Flash: 76.0%Vals AIAs of 10/13/2026
LiveCodeBenchMedium · higher is betterTest setup not documented as identicalGPT-5.4: 85.6%Gemini 3.5 Flash: 90.6%Vals AIAs of 09/01/2026
LMArena Text, Style ControlCoding · higher is betterGPT-5.4: 1,521Gemini 3.5 Flash: 1,508LMArenaAs of 11/11/2026
LMArena Vision, Style ControlDiagram understanding · higher is betterGPT-5.4: 1,319Gemini 3.5 Flash: 1,307LMArenaAs of 11/09/2026
MMLU ProChemistry · higher is betterTest setup not documented as identicalGPT-5.4: 91.1%Gemini 3.5 Flash: 93.1%Vals AIAs of 09/01/2026
ProgramBenchRaw Pass Rate · higher is betterTest setup not documented as identicalGPT-5.4: 68.6%Gemini 3.5 Flash: 56.4%Vals AIAs of 11/05/2026
SWE-bench Verified1-4 hours · higher is betterTest setup not documented as identicalGPT-5.4: 50.0%Gemini 3.5 Flash: 52.4%Vals AIAs of 09/01/2026
LegalBenchRhetoric Tasks · higher is betterTest setup not documented as identicalGPT-5.4: 82.8%Gemini 3.5 Flash: 83.4%Vals AIAs of 10/13/2026
LMArena Text, Style ControlCreative writing · higher is betterGPT-5.4: 1,440Gemini 3.5 Flash: 1,465LMArenaAs of 11/11/2026
LMArena Vision, Style ControlEnglish · higher is betterGPT-5.4: 1,279Gemini 3.5 Flash: 1,277LMArenaAs of 11/09/2026
MMLU ProComputer Science · higher is betterTest setup not documented as identicalGPT-5.4: 89.8%Gemini 3.5 Flash: 91.7%Vals AIAs of 09/01/2026
SWE-bench Verified15 min - 1 hour · higher is betterTest setup not documented as identicalGPT-5.4: 76.2%Gemini 3.5 Flash: 77.8%Vals AIAs of 09/01/2026
LegalBenchRule Tasks · higher is betterTest setup not documented as identicalGPT-5.4: 84%Gemini 3.5 Flash: 88%Vals AIAs of 10/13/2026
LMArena Text, Style ControlEnglish · higher is betterGPT-5.4: 1,476Gemini 3.5 Flash: 1,478LMArenaAs of 11/11/2026
LMArena Vision, Style ControlHomework · higher is betterGPT-5.4: 1,330Gemini 3.5 Flash: 1,307LMArenaAs of 11/09/2026
MMLU ProEconomics · higher is betterTest setup not documented as identicalGPT-5.4: 89.7%Gemini 3.5 Flash: 91.9%Vals AIAs of 09/01/2026
LMArena Text, Style ControlEntertainment, sports and media · higher is betterGPT-5.4: 1,441Gemini 3.5 Flash: 1,455LMArenaAs of 11/11/2026
LMArena Vision, Style ControlHumor · higher is betterGPT-5.4: 1,267Gemini 3.5 Flash: 1,293LMArenaAs of 11/09/2026

More comparisons

Compare GPT-5.4 and Gemini 3.5 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
  2. 2GPT-5.4 vs. GLM-5.3-Flash
  3. 3GPT-6.1 Sol vs. GPT-5.4
  4. 4GPT-6 Sol vs. GPT-5.4
  5. 5GPT-6.1 Sol vs. Gemini 3.5 Flash
  6. 6GPT-6.1 Terra vs. GPT-5.4
  7. 7GPT-6 Luna vs. Gemini 3.5 Flash
  8. 8Gemini 3.5 Flash vs. DeepSeek-V4-Flash
  9. 9Gemini 3.5 Flash vs. Qwen 3.8 27B
Show all 26 comparisons
  1. 10GPT-5.6 Luna vs. GPT-5.4
  2. 11GPT-5.4 vs. GLM-5.3
  3. 12Claude Sonnet 5.5 vs. GPT-5.4
  4. 13GPT-6 Astra vs. GPT-5.4
  5. 14Claude Opus 5.5 vs. GPT-5.4
  6. 15GPT-5.6 Terra vs. GPT-5.4
  7. 16Gemini 4 Carbon vs. Gemini 3.5 Flash
  8. 17Claude Opus 5.5 vs. Gemini 3.5 Flash
  9. 18Gemini 3.8 Flash vs. Gemini 3.5 Flash
  10. 19Gemini 3.5 Flash vs. DeepSeek-V4.1-Flash
  11. 20Claude Haiku 5.5 vs. Gemini 3.5 Flash
  12. 21GPT-5.6 Luna vs. Gemini 3.5 Flash
  13. 22GPT-5.6 Sol vs. GPT-5.4
  14. 23Claude Sonnet 5.5 vs. Gemini 3.5 Flash
  15. 24Claude Sonnet 4.6 vs. Gemini 3.5 Flash
  16. 25Gemini 3.5 Flash vs. MiMo-V2.5-Pro
  17. 26Claude Fable 5 vs. GPT-5.4