Enter opens the highlighted result. Esc closes.

Gemini 3.6 Flash vs GPT-5.4 Mini

Gemini 3.6 Flash leads GPT-5.4 Mini on coding, 62.5 to 35.8 on the Vibe Coding Index, and Gemini 3.6 Flash costs 1.2x less per output token ($3.75 vs $4.50 per million). Updated October 21, 2026; 80 benchmarks have a result for both.

Replace Gemini 3.6 Flash Replace GPT-5.4 Mini
Gemini 3.6 FlashGoogle
Coding
62.5
Overall
68.3
Output $/M
$3.75
76
GPT-5.4 MiniOpenAI
Coding
35.8
Overall
44.0
Output $/M
$4.50
3
vs boards won of 80 shared, 1 tied

Gemini 3.6 Flash or GPT-5.4 Mini: which to pick

Pick Gemini 3.6 Flash for coding: it scores 62.5 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 a lower cost per solved task ($0.70 against $1.49) and work measured by WeirdML or ALE-Bench, where it leads.

Model AGemini 3.6 FlashGoogle62.5/1004 independent benchmarks$1.49 per solved taskModel BGPT-5.4 MiniOpenAI35.8/1005 independent benchmarks$0.70 per solved task
Shared results
80
Gemini 3.6 Flash only
29
GPT-5.4 Mini only
9
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 3.6 Flash 62.5 from 4 benchmarks, GPT-5.4 Mini 35.8 from 5 benchmarks.
Widest category
Reasoning, 13.9 points apart on average over 14 shared benchmarks.
Widest single gap
ARC-AGI-2: Gemini 3.6 Flash 60.4% against GPT-5.4 Mini 18.9%, 41.5 points apart on a 0 to 100 scale.
Output price
Gemini 3.6 Flash $3.75 against GPT-5.4 Mini $4.50 per million output tokens, 1.2x apart.
Context window
Gemini 3.6 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 3.6 FlashBarsGPT-5.4 MiniTies
Coding1321 tie
Intelligence20
Agentic work50
Reasoning140
Math60
Knowledge90
General271
All shared boards7631 tie
CodingLike-for-likeSix of these boards feed the Vibe Coding Index132
Coding benchmarks for Gemini 3.6 Flash and GPT-5.4 Mini
BenchmarkGemini 3.6 FlashGPT-5.4 MiniLeader
LMArena WebDev15381397Gemini 3.6 Flash
AA Coding Index69.256.1Gemini 3.6 Flash
LiveCodeBench (Vals AI)88.1%81.5%Gemini 3.6 Flash
SWE-bench Verified (Vals AI)79.6%73.0%Gemini 3.6 Flash
Terminal-Bench 4 (Vals AI)Not measured2.5%Only GPT-5.4 Mini measured
Vibe Code Bench (Vals AI)64.0%48.0%Gemini 3.6 Flash
Code migration (Vals AI)30.9%12.9%Gemini 3.6 Flash
ProgramBench (Vals AI)0.0%0.0%Tie
IOI (Vals AI)35.1%Not measuredOnly Gemini 3.6 Flash measured
Terminal-Bench 2.1 (Vals AI)73.8%54.7%Gemini 3.6 Flash
CyberBench (Vals AI)45.4%Not measuredOnly Gemini 3.6 Flash measured
SciCode53.4%52.1%Gemini 3.6 Flash
Terminal-Bench Hard (Artificial Analysis run)Not measured52.3%Only GPT-5.4 Mini measured
FrontierCode34.4%27.0%Gemini 3.6 Flash
WeirdML56.1%60.3%GPT-5.4 Mini
ALE-Bench715.51188.6GPT-5.4 Mini
LMArena Text: coding14911438Gemini 3.6 Flash
LMArena Text: software and IT14921436Gemini 3.6 Flash
LMArena WebDev: React15281386Gemini 3.6 Flash
LMArena WebDev: HTML15471419Gemini 3.6 Flash
LMArena WebDev: from an image1545Not measuredOnly Gemini 3.6 Flash measured
SciCode10.8%Not measuredOnly Gemini 3.6 Flash measured
Neither model has a result on the other 17 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Gemini 3.6 Flash and GPT-5.4 Mini
BenchmarkGemini 3.6 FlashGPT-5.4 MiniLeader
AA Intelligence Index34.024.1Gemini 3.6 Flash
Epoch Capabilities Index154.5148.7Gemini 3.6 Flash
Agentic workLike-for-likePublic boards, shown as published, kept out of the index50
Agentic work benchmarks for Gemini 3.6 Flash and GPT-5.4 Mini
BenchmarkGemini 3.6 FlashGPT-5.4 MiniLeader
AA Agentic Index29.017.9Gemini 3.6 Flash
Design Arena: agents building web apps1197Not measuredOnly Gemini 3.6 Flash measured
Design Arena: agents building full-stack apps1181Not measuredOnly Gemini 3.6 Flash measured
Design Arena: agents building mobile apps1199Not measuredOnly Gemini 3.6 Flash measured
Design Arena: agents building Android apps1203Not measuredOnly Gemini 3.6 Flash measured
Design Arena: agents building games1181Not measuredOnly Gemini 3.6 Flash measured
Design Arena: HTML slides1148Not measuredOnly Gemini 3.6 Flash measured
Design Arena: PowerPoint slides1146Not measuredOnly Gemini 3.6 Flash measured
Design Arena: spreadsheets1034Not measuredOnly Gemini 3.6 Flash measured
Finance Agent (Vals AI)56.3%45.4%Gemini 3.6 Flash
Tax Agent Bench (Vals AI)18.0%8.8%Gemini 3.6 Flash
Legal Research Bench (Vals AI)25.0%12.5%Gemini 3.6 Flash
Excel Modeling Benchmark (Vals AI)65.4%45.4%Gemini 3.6 Flash
BioMysteryBench (Vals AI)58.5%Not measuredOnly Gemini 3.6 Flash measured
Terminal-Bench-Science (Vals AI)4.3%Not measuredOnly Gemini 3.6 Flash measured
τ²-Bench TelecomNot measured83.3%Only GPT-5.4 Mini measured
APEX-Agents46.9%Not measuredOnly Gemini 3.6 Flash measured
DeepResearch BenchNot measured36.3%Only GPT-5.4 Mini 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 3.6 Flash and GPT-5.4 Mini
BenchmarkGemini 3.6 FlashGPT-5.4 MiniLeader
GPQA Diamond93.4%83.1%Gemini 3.6 Flash
MMMU Pro (Vals AI)88.4%79.3%Gemini 3.6 Flash
GPQA Diamond (Artificial Analysis run)92.8%87.5%Gemini 3.6 Flash
Humanity's Last Exam (Artificial Analysis run)40.8%28.1%Gemini 3.6 Flash
GPQA Diamond (Epoch AI run)94.1%86.9%Gemini 3.6 Flash
ARC-AGI91.2%63.7%Gemini 3.6 Flash
ARC-AGI-260.4%18.9%Gemini 3.6 Flash
Chess puzzles42.0%23.0%Gemini 3.6 Flash
Mystery game puzzles30.0%11.0%Gemini 3.6 Flash
LMArena Text: hard prompts14861424Gemini 3.6 Flash
LMArena Text: expert14901435Gemini 3.6 Flash
LMArena Text: hard prompts in English14841420Gemini 3.6 Flash
LMArena Vision: diagrams13141266Gemini 3.6 Flash
LMArena Vision: homework13141285Gemini 3.6 Flash
Kagi LLM BenchmarkNot measured37.9%Only GPT-5.4 Mini measured
Neither model has a result on the other 7 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index60
Math benchmarks for Gemini 3.6 Flash and GPT-5.4 Mini
BenchmarkGemini 3.6 FlashGPT-5.4 MiniLeader
AIMENot measured95.6%Only GPT-5.4 Mini measured
OTIS Mock AIME94.2%88.9%Gemini 3.6 Flash
FrontierMath, tiers 1 to 358.9%51.2%Gemini 3.6 Flash
FrontierMath, tier 422.0%9.8%Gemini 3.6 Flash
ProofBench36.0%21.0%Gemini 3.6 Flash
LMArena Text: math15081418Gemini 3.6 Flash
LMArena Text: mathematical work14921429Gemini 3.6 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 3.6 Flash and GPT-5.4 Mini
BenchmarkGemini 3.6 FlashGPT-5.4 MiniLeader
MMLU Pro89.3%84.5%Gemini 3.6 Flash
LegalBench (Vals AI)86.7%Not measuredOnly Gemini 3.6 Flash measured
CaseLaw (Vals AI)Not measured51.7%Only GPT-5.4 Mini measured
CorpFin (Vals AI)63.3%60.9%Gemini 3.6 Flash
TaxEval (Vals AI)74.9%71.2%Gemini 3.6 Flash
MortgageTax (Vals AI)67.6%63.5%Gemini 3.6 Flash
MedCode (Vals AI)53.1%Not measuredOnly Gemini 3.6 Flash measured
SimpleQA Verified66.2%29.4%Gemini 3.6 Flash
LMArena Text: science14891417Gemini 3.6 Flash
LMArena Text: medicine and healthcare14691395Gemini 3.6 Flash
LMArena Text: legal and government14791414Gemini 3.6 Flash
LMArena Text: business and finance14641418Gemini 3.6 Flash
FACTS Benchmark Suite65.3%Not measuredOnly Gemini 3.6 Flash measured
Neither model has a result on the other 5 boards here
Web designDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
Web design benchmarks for Gemini 3.6 Flash and GPT-5.4 Mini
BenchmarkGemini 3.6 FlashGPT-5.4 MiniLeader
Design Arena: websites1300Not measuredOnly Gemini 3.6 Flash measured
Design Arena: UI components1297Not measuredOnly Gemini 3.6 Flash measured
Design Arena: game dev1263Not measuredOnly Gemini 3.6 Flash measured
Design Arena: data viz1289Not measuredOnly Gemini 3.6 Flash measured
Design Arena: 3D1272Not measuredOnly Gemini 3.6 Flash measured
Design Arena: all code categories1290Not measuredOnly Gemini 3.6 Flash measured
Design Arena: ASCII art1281Not measuredOnly Gemini 3.6 Flash measured
Neither model has a result on the other 2 boards here
GeneralLike-for-likePublic boards, shown as published, kept out of the index271
General benchmarks for Gemini 3.6 Flash and GPT-5.4 Mini
BenchmarkGemini 3.6 FlashGPT-5.4 MiniLeader
Public Benefits Bench (Vals AI)56.6%Not measuredOnly Gemini 3.6 Flash measured
SAGE (Vals AI)48.7%50.8%GPT-5.4 Mini
MedScribe (Vals AI)79.7%Not measuredOnly Gemini 3.6 Flash measured
Vals Multimodal Index65.1%54.2%Gemini 3.6 Flash
IFBenchNot measured73.3%Only GPT-5.4 Mini measured
Long context reasoning (AA-LCR)80.0%77.0%Gemini 3.6 Flash
DTBench95.5%80.0%Gemini 3.6 Flash
LMCA44.9%40.8%Gemini 3.6 Flash
Furniture assembly23.3%Not measuredOnly Gemini 3.6 Flash measured
LMArena Text14801412Gemini 3.6 Flash
LMArena Text: instruction following14671405Gemini 3.6 Flash
LMArena Text: creative writing14661370Gemini 3.6 Flash
LMArena Vision12991245Gemini 3.6 Flash
LMArena Text: English14821412Gemini 3.6 Flash
LMArena Text: non-English14701405Gemini 3.6 Flash
LMArena Text: Chinese15311446Gemini 3.6 Flash
LMArena Text: German14801408Gemini 3.6 Flash
LMArena Text: Japanese14751375Gemini 3.6 Flash
LMArena Text: Korean14291370Gemini 3.6 Flash
LMArena Text: French15031441Gemini 3.6 Flash
LMArena Text: Spanish14761405Gemini 3.6 Flash
LMArena Text: Russian14881417Gemini 3.6 Flash
LMArena Text: Polish14731415Gemini 3.6 Flash
LMArena Text: multi-turn14811429Gemini 3.6 Flash
LMArena Text: longer queries14751408Gemini 3.6 Flash
LMArena Text: writing and language14701393Gemini 3.6 Flash
LMArena Text: entertainment and media14561373Gemini 3.6 Flash
LMArena Vision: English12951244Gemini 3.6 Flash
LMArena Vision: Chinese13571286Gemini 3.6 Flash
LMArena Vision: reading text13121253Gemini 3.6 Flash
LMArena Vision: humor12891235Gemini 3.6 Flash
LMArena Vision: recognizing thingsNot measured1218Only GPT-5.4 Mini measured
LMArena Vision: creative writing12781222Gemini 3.6 Flash
LMArena Document1456Not measuredOnly Gemini 3.6 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 3.6 Flash and GPT-5.4 Mini
BenchmarkGemini 3.6 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 3.6 Flash$0.0026Fits in one request
GPT-5.4 Mini$0.0030Fits in one request

Gemini 3.6 Flash costs less

Repository review

50K input + 3K output tokens

Gemini 3.6 Flash$0.049Fits in one request
GPT-5.4 Mini$0.051Fits in one request

Gemini 3.6 Flash costs less

Agent loop

200K input + 10K output tokens

Gemini 3.6 Flash$0.188Fits in one request
GPT-5.4 Mini$0.195Fits in one request

Gemini 3.6 Flash 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 3.6 Flash and GPT-5.4 Mini
SpecificationGoogle Gemini 3.6 FlashOpenAI GPT-5.4 Mini
MakerGoogleOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedJuly 21, 2026March 17, 2026
Context window1.05M400K
Input $/Mtok$0.75$0.75
Output $/Mtok$3.75$4.50
Coding index62.535.8
Independent measurements behind it45
Cost per solved task$1.49$0.70
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemini 3.6 Flash better than GPT-5.4 Mini for coding?

Pick Gemini 3.6 Flash for coding: it scores 62.5 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 a lower cost per solved task ($0.70 against $1.49) and work measured by WeirdML or ALE-Bench, where it leads.

Which is cheaper, Gemini 3.6 Flash or GPT-5.4 Mini?

Gemini 3.6 Flash costs $0.75 per million input tokens and $3.75 per million output tokens; GPT-5.4 Mini costs $0.75 and $4.50. Per solved SWE-bench Verified task, Gemini 3.6 Flash costs $1.49 and GPT-5.4 Mini $0.70.

Which has the bigger context window, Gemini 3.6 Flash or GPT-5.4 Mini?

Gemini 3.6 Flash, with 1.05M tokens against 400K.

How many benchmarks is the Gemini 3.6 Flash vs GPT-5.4 Mini comparison based on?

80 benchmarks have a result for both models as of October 21, 2026. Gemini 3.6 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-3-6-flash-vs-gpt-5-4-mini" title="Gemini 3.6 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-3-6-flash-vs-gpt-5-4-mini">LLMBenchmark.ai, Gemini 3.6 Flash vs GPT-5.4 Mini</a></p>