Enter opens the highlighted result. Esc closes.

Gemini 3.5 Flash vs GPT-5.4 Mini

Gemini 3.5 Flash leads GPT-5.4 Mini on coding, 39.8 to 35.8 on the Vibe Coding Index, and GPT-5.4 Mini costs 2.0x less per output token ($4.50 vs $9.00 per million). Updated October 22, 2026; 81 benchmarks have a result for both.

Replace Gemini 3.5 Flash Replace GPT-5.4 Mini
Gemini 3.5 FlashGoogle
Coding
39.8
Overall
63.8
Output $/M
$9.00
76
GPT-5.4 MiniOpenAI
Coding
35.8
Overall
44.0
Output $/M
$4.50
4
vs boards won of 81 shared, 1 tied

Gemini 3.5 Flash or GPT-5.4 Mini: which to pick

Pick Gemini 3.5 Flash for coding: it scores 39.8 on the Vibe Coding Index against 35.8 for GPT-5.4 Mini, though on 4 benchmarks against 5.

Pick GPT-5.4 Mini for output tokens 2.0x cheaper ($4.50 vs $9.00 per million) and a lower cost per solved task ($0.70 against $1.21).

Model AGemini 3.5 FlashGoogle39.8/1004 independent benchmarks$1.21 per solved taskModel BGPT-5.4 MiniOpenAI35.8/1005 independent benchmarks$0.70 per solved task
Shared results
81
Gemini 3.5 Flash only
31
GPT-5.4 Mini only
8
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.

At a glance

Coding index
Gemini 3.5 Flash 39.8 from 4 benchmarks, GPT-5.4 Mini 35.8 from 5 benchmarks.
Widest category
Reasoning, 15.5 points apart on average over 14 shared benchmarks.
Widest single gap
ARC-AGI-2: Gemini 3.5 Flash 72.1% against GPT-5.4 Mini 18.9%, 53.2 points apart on a 0 to 100 scale.
Output price
Gemini 3.5 Flash $9.00 against GPT-5.4 Mini $4.50 per million output tokens, 2.0x apart.
Context window
Gemini 3.5 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
CategoryGemini 3.5 FlashBarsGPT-5.4 MiniTies
Coding1321 tie
Intelligence20
Agentic work50
Reasoning140
Math60
Knowledge90
General272
All shared boards7641 tie
CodingLike-for-likeSix of these boards feed the Vibe Coding Index132
Coding benchmarks for Gemini 3.5 Flash and GPT-5.4 Mini
BenchmarkGemini 3.5 FlashGPT-5.4 MiniLeader
LMArena WebDev14991397Gemini 3.5 Flash
AA Coding IndexNot measured56.1Only GPT-5.4 Mini measured
LiveCodeBench (Vals AI)87.6%81.5%Gemini 3.5 Flash
SWE-bench Verified (Vals AI)78.8%73.0%Gemini 3.5 Flash
Terminal-Bench 4 (Vals AI)6.1%2.5%Gemini 3.5 Flash
Vibe Code Bench (Vals AI)48.7%48.0%Gemini 3.5 Flash
Code migration (Vals AI)26.8%12.9%Gemini 3.5 Flash
ProgramBench (Vals AI)0.0%0.0%Tie
Terminal-Bench 2.1 (Vals AI)74.2%54.7%Gemini 3.5 Flash
SkillsBench (Vals AI)52.7%Not measuredOnly Gemini 3.5 Flash measured
SciCode53.9%52.1%Gemini 3.5 Flash
Terminal-Bench Hard (Artificial Analysis run)46.2%52.3%GPT-5.4 Mini
FrontierCodeNot measured27.0%Only GPT-5.4 Mini measured
WeirdML62.6%60.3%Gemini 3.5 Flash
ALE-Bench911.01188.6GPT-5.4 Mini
LMArena Text: coding14931438Gemini 3.5 Flash
LMArena Text: software and IT14941436Gemini 3.5 Flash
LMArena WebDev: React14951386Gemini 3.5 Flash
LMArena WebDev: HTML15221419Gemini 3.5 Flash
LMArena WebDev: from an image1504Not measuredOnly Gemini 3.5 Flash measured
SciCode12.3%Not measuredOnly Gemini 3.5 Flash measured
Neither model has a result on the other 18 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Gemini 3.5 Flash and GPT-5.4 Mini
BenchmarkGemini 3.5 FlashGPT-5.4 MiniLeader
AA Intelligence Index33.624.1Gemini 3.5 Flash
Epoch Capabilities Index154.9148.7Gemini 3.5 Flash
Agentic workLike-for-likePublic boards, shown as published, kept out of the index50
Agentic work benchmarks for Gemini 3.5 Flash and GPT-5.4 Mini
BenchmarkGemini 3.5 FlashGPT-5.4 MiniLeader
AA Agentic IndexNot measured17.9Only GPT-5.4 Mini measured
Design Arena: agents building web apps1202Not measuredOnly Gemini 3.5 Flash measured
Design Arena: agents building full-stack apps1197Not measuredOnly Gemini 3.5 Flash measured
Design Arena: agents building mobile apps1174Not measuredOnly Gemini 3.5 Flash measured
Design Arena: agents building Android apps1185Not measuredOnly Gemini 3.5 Flash measured
Design Arena: agents building Godot games1098Not measuredOnly Gemini 3.5 Flash measured
Design Arena: agents building games1180Not measuredOnly Gemini 3.5 Flash measured
Design Arena: HTML slides1093Not measuredOnly Gemini 3.5 Flash measured
Design Arena: PowerPoint slides1154Not measuredOnly Gemini 3.5 Flash measured
Finance Agent (Vals AI)57.9%45.4%Gemini 3.5 Flash
Tax Agent Bench (Vals AI)21.6%8.8%Gemini 3.5 Flash
Legal Research Bench (Vals AI)30.8%12.5%Gemini 3.5 Flash
Excel Modeling Benchmark (Vals AI)63.5%45.4%Gemini 3.5 Flash
Terminal-Bench-Science (Vals AI)5.7%Not measuredOnly Gemini 3.5 Flash measured
τ²-Bench Telecom95.6%83.3%Gemini 3.5 Flash
APEX-Agents27.5%Not measuredOnly Gemini 3.5 Flash measured
DeepResearch BenchNot measured36.3%Only GPT-5.4 Mini measured
Vending-Bench 2$5,396Not measuredOnly Gemini 3.5 Flash measured
Neither model has a result on the other 23 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index140
Reasoning benchmarks for Gemini 3.5 Flash and GPT-5.4 Mini
BenchmarkGemini 3.5 FlashGPT-5.4 MiniLeader
GPQA Diamond92.7%83.1%Gemini 3.5 Flash
MMMU Pro (Vals AI)88.3%79.3%Gemini 3.5 Flash
GPQA Diamond (Artificial Analysis run)92.2%87.5%Gemini 3.5 Flash
Humanity's Last Exam (Artificial Analysis run)42.7%28.1%Gemini 3.5 Flash
GPQA Diamond (Epoch AI run)92.8%86.9%Gemini 3.5 Flash
ARC-AGI92.5%63.7%Gemini 3.5 Flash
ARC-AGI-272.1%18.9%Gemini 3.5 Flash
SimpleBench76.7%Not measuredOnly Gemini 3.5 Flash measured
Chess puzzles45.0%23.0%Gemini 3.5 Flash
Mystery game puzzles32.0%11.0%Gemini 3.5 Flash
EBR-bench4.8%Not measuredOnly Gemini 3.5 Flash measured
LMArena Text: hard prompts14881424Gemini 3.5 Flash
LMArena Text: expert14951435Gemini 3.5 Flash
LMArena Text: hard prompts in English14831420Gemini 3.5 Flash
LMArena Vision: diagrams13231266Gemini 3.5 Flash
LMArena Vision: homework13301285Gemini 3.5 Flash
Kagi LLM BenchmarkNot measured37.9%Only GPT-5.4 Mini measured
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 3.5 Flash and GPT-5.4 Mini
BenchmarkGemini 3.5 FlashGPT-5.4 MiniLeader
AIMENot measured95.6%Only GPT-5.4 Mini measured
OTIS Mock AIME95.6%88.9%Gemini 3.5 Flash
FrontierMath, tiers 1 to 362.8%51.2%Gemini 3.5 Flash
FrontierMath, tier 426.8%9.8%Gemini 3.5 Flash
ProofBench31.0%21.0%Gemini 3.5 Flash
LMArena Text: math15041418Gemini 3.5 Flash
LMArena Text: mathematical work14951429Gemini 3.5 Flash
Neither model has a result on the other 6 boards here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index90
Knowledge benchmarks for Gemini 3.5 Flash and GPT-5.4 Mini
BenchmarkGemini 3.5 FlashGPT-5.4 MiniLeader
MMLU Pro89.5%84.5%Gemini 3.5 Flash
LegalBench (Vals AI)83.6%Not measuredOnly Gemini 3.5 Flash measured
CaseLaw (Vals AI)Not measured51.7%Only GPT-5.4 Mini measured
CorpFin (Vals AI)64.7%60.9%Gemini 3.5 Flash
TaxEval (Vals AI)74.4%71.2%Gemini 3.5 Flash
MortgageTax (Vals AI)68.1%63.5%Gemini 3.5 Flash
MedCode (Vals AI)55.8%Not measuredOnly Gemini 3.5 Flash measured
SimpleQA Verified66.2%29.4%Gemini 3.5 Flash
LMArena Text: science14951417Gemini 3.5 Flash
LMArena Text: medicine and healthcare14831395Gemini 3.5 Flash
LMArena Text: legal and government14881414Gemini 3.5 Flash
LMArena Text: business and finance14671418Gemini 3.5 Flash
FACTS Benchmark Suite63.1%Not measuredOnly Gemini 3.5 Flash measured
Neither model has a result on the other 5 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
Web design benchmarks for Gemini 3.5 Flash and GPT-5.4 Mini
BenchmarkGemini 3.5 FlashGPT-5.4 MiniLeader
Design Arena: websites1267Not measuredOnly Gemini 3.5 Flash measured
Design Arena: UI components1269Not measuredOnly Gemini 3.5 Flash measured
Design Arena: game dev1263Not measuredOnly Gemini 3.5 Flash measured
Design Arena: data viz1236Not measuredOnly Gemini 3.5 Flash measured
Design Arena: 3D1243Not measuredOnly Gemini 3.5 Flash measured
Design Arena: all code categories1266Not measuredOnly Gemini 3.5 Flash measured
Design Arena: SVG1253Not measuredOnly Gemini 3.5 Flash measured
Design Arena: ASCII art1254Not measuredOnly Gemini 3.5 Flash measured
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index272
General benchmarks for Gemini 3.5 Flash and GPT-5.4 Mini
BenchmarkGemini 3.5 FlashGPT-5.4 MiniLeader
Public Benefits Bench (Vals AI)59.5%Not measuredOnly Gemini 3.5 Flash measured
SAGE (Vals AI)49.9%50.8%GPT-5.4 Mini
MedScribe (Vals AI)76.6%Not measuredOnly Gemini 3.5 Flash measured
Vals Multimodal Index62.9%54.2%Gemini 3.5 Flash
IFBench76.3%73.3%Gemini 3.5 Flash
Long context reasoning (AA-LCR)74.3%77.0%GPT-5.4 Mini
DTBench94.7%80.0%Gemini 3.5 Flash
LMCA47.1%40.8%Gemini 3.5 Flash
Surface Evolver Bench58.1%Not measuredOnly Gemini 3.5 Flash measured
LMArena Text14821412Gemini 3.5 Flash
LMArena Text: instruction following14671405Gemini 3.5 Flash
LMArena Text: creative writing14701370Gemini 3.5 Flash
LMArena Vision13081245Gemini 3.5 Flash
LMArena Text: English14811412Gemini 3.5 Flash
LMArena Text: non-English14751405Gemini 3.5 Flash
LMArena Text: Chinese15271446Gemini 3.5 Flash
LMArena Text: German14941408Gemini 3.5 Flash
LMArena Text: Japanese14861375Gemini 3.5 Flash
LMArena Text: Korean14481370Gemini 3.5 Flash
LMArena Text: French14901441Gemini 3.5 Flash
LMArena Text: Spanish14801405Gemini 3.5 Flash
LMArena Text: Russian14931417Gemini 3.5 Flash
LMArena Text: Polish15161415Gemini 3.5 Flash
LMArena Text: multi-turn14811429Gemini 3.5 Flash
LMArena Text: longer queries14831408Gemini 3.5 Flash
LMArena Text: writing and language14781393Gemini 3.5 Flash
LMArena Text: entertainment and media14591373Gemini 3.5 Flash
LMArena Vision: English13051244Gemini 3.5 Flash
LMArena Vision: Chinese13771286Gemini 3.5 Flash
LMArena Vision: reading text13171253Gemini 3.5 Flash
LMArena Vision: humor13211235Gemini 3.5 Flash
LMArena Vision: recognizing thingsNot measured1218Only GPT-5.4 Mini measured
LMArena Vision: creative writing13011222Gemini 3.5 Flash
LMArena Document1463Not measuredOnly Gemini 3.5 Flash measured
Neither model has a result on the other 12 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Gemini 3.5 Flash and GPT-5.4 Mini
BenchmarkGemini 3.5 FlashGPT-5.4 MiniLeader
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 3.5 Flash$0.0060Fits 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 3.5 Flash$0.102Fits 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 3.5 Flash$0.390Fits 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 3.5 Flash and GPT-5.4 Mini
SpecificationGoogle Gemini 3.5 FlashOpenAI GPT-5.4 Mini
MakerGoogleOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedMay 19, 2026March 17, 2026
Context window1.05M400K
Input $/Mtok$1.50$0.75
Output $/Mtok$9.00$4.50
Coding index39.835.8
Independent measurements behind it45
Cost per solved task$1.21$0.70
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemini 3.5 Flash better than GPT-5.4 Mini for coding?

Pick Gemini 3.5 Flash for coding: it scores 39.8 on the Vibe Coding Index against 35.8 for GPT-5.4 Mini, though on 4 benchmarks against 5. Pick GPT-5.4 Mini for output tokens 2.0x cheaper ($4.50 vs $9.00 per million) and a lower cost per solved task ($0.70 against $1.21).

Which is cheaper, Gemini 3.5 Flash or GPT-5.4 Mini?

Gemini 3.5 Flash costs $1.50 per million input tokens and $9.00 per million output tokens; GPT-5.4 Mini costs $0.75 and $4.50. Per solved SWE-bench Verified task, Gemini 3.5 Flash costs $1.21 and GPT-5.4 Mini $0.70.

Which has the bigger context window, Gemini 3.5 Flash or GPT-5.4 Mini?

Gemini 3.5 Flash, with 1.05M tokens against 400K.

How many benchmarks is the Gemini 3.5 Flash vs GPT-5.4 Mini comparison based on?

81 benchmarks have a result for both models as of October 22, 2026. Gemini 3.5 Flash'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-3-5-flash-vs-gpt-5-4-mini" title="Gemini 3.5 Flash 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-3-5-flash-vs-gpt-5-4-mini">LLMBenchmark.ai, Gemini 3.5 Flash vs GPT-5.4 Mini</a></p>