LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Gemini 3.7 Flash vs GPT-5.4 Mini

Updated October 21, 2026. 77 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Gemini 3.7 Flash Replace GPT-5.4 Mini
Gemini 3.7 FlashGoogle
Coding
69.9
Overall
39.6
Output $/M
$3.75
74
GPT-5.4 MiniOpenAI
Coding
28.2
Overall
24.1
Output $/M
$4.50
2
vs boards won of 77 shared, 1 tied

Decision reading

Pick Gemini 3.7 Flash for coding: it scores 69.9 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 $1.78, or when what matters is ALE-Bench or SAGE (Vals AI), where it leads.

Model AGemini 3.7 FlashGoogle69.9/1002 independent benchmarks$1.78 per solved taskModel BGPT-5.4 MiniOpenAI28.2/1001 independent benchmark$0.70 per solved task
Shared results
77
Gemini 3.7 Flash only
35
GPT-5.4 Mini only
11
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.

At a glance

Coding index
Gemini 3.7 Flash 69.9 from 2 benchmarks, GPT-5.4 Mini 28.2 from 1 benchmark.
Widest category
Math, 20.0 points apart on average over 6 shared benchmarks.
Widest single gap
ARC-AGI-2: Gemini 3.7 Flash 84.6% against GPT-5.4 Mini 18.9%, 65.7 points apart on a 0 to 100 scale.
Output price
Gemini 3.7 Flash $3.75 against GPT-5.4 Mini $4.50 per million output tokens, 1.2x apart.
Context window
Gemini 3.7 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 3.7 FlashBarsGPT-5.4 MiniTies
Coding1411 tie
Intelligence20
Agentic work40
Reasoning140
Math60
Knowledge80
General261
All shared boards7421 tie
CodingLike-for-likeFour of these boards feed the Vibe Coding Index141
Coding benchmarks for Gemini 3.7 Flash and GPT-5.4 Mini
BenchmarkGemini 3.7 FlashGPT-5.4 MiniLeader
LiveBench coding80.5%Not measuredOnly Gemini 3.7 Flash measured
LMArena WebDev15911397Gemini 3.7 Flash
AA Coding Index71.556.1Gemini 3.7 Flash
LiveCodeBench (Vals AI)88.7%81.5%Gemini 3.7 Flash
SWE-bench Verified (Vals AI)80.8%73.0%Gemini 3.7 Flash
Terminal-Bench 4 (Vals AI)12.1%2.5%Gemini 3.7 Flash
Vibe Code Bench (Vals AI)70.4%48.0%Gemini 3.7 Flash
Code migration (Vals AI)34.8%12.9%Gemini 3.7 Flash
ProgramBench (Vals AI)0.0%0.0%Tie
IOI (Vals AI)67.8%Not measuredOnly Gemini 3.7 Flash measured
Terminal-Bench 2.1 (Vals AI)77.5%54.7%Gemini 3.7 Flash
SkillsBench (Vals AI)65.9%Not measuredOnly Gemini 3.7 Flash measured
CyberBench (Vals AI)43.8%Not measuredOnly Gemini 3.7 Flash measured
SciCode59.8%52.1%Gemini 3.7 Flash
Terminal-Bench Hard (Artificial Analysis run)Not measured52.3%Only GPT-5.4 Mini measured
FrontierCode43.6%27.0%Gemini 3.7 Flash
FrontierSWE20.3%Not measuredOnly Gemini 3.7 Flash measured
WeirdMLNot measured60.3%Only GPT-5.4 Mini measured
ALE-Bench904.31188.6GPT-5.4 Mini
LMArena Text: coding14991438Gemini 3.7 Flash
LMArena Text: software and IT14981436Gemini 3.7 Flash
LMArena WebDev: React15871386Gemini 3.7 Flash
LMArena WebDev: HTML15931419Gemini 3.7 Flash
LMArena WebDev: from an image1599Not measuredOnly Gemini 3.7 Flash measured
Neither model has a result on the other 14 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Gemini 3.7 Flash and GPT-5.4 Mini
BenchmarkGemini 3.7 FlashGPT-5.4 MiniLeader
AA Intelligence Index39.624.1Gemini 3.7 Flash
Epoch Capabilities Index158.0148.7Gemini 3.7 Flash
Agentic workLike-for-likePublic boards, shown as published, kept out of the index40
Agentic work benchmarks for Gemini 3.7 Flash and GPT-5.4 Mini
BenchmarkGemini 3.7 FlashGPT-5.4 MiniLeader
AA Agentic IndexNot measured17.9Only GPT-5.4 Mini measured
Design Arena: agents building web apps1224Not measuredOnly Gemini 3.7 Flash measured
Design Arena: agents building full-stack apps1208Not measuredOnly Gemini 3.7 Flash measured
Design Arena: agents building mobile apps1230Not measuredOnly Gemini 3.7 Flash measured
Design Arena: agents building Android apps1247Not measuredOnly Gemini 3.7 Flash measured
Design Arena: agents building Godot games1264Not measuredOnly Gemini 3.7 Flash measured
Design Arena: agents building games1235Not measuredOnly Gemini 3.7 Flash measured
Design Arena: spreadsheets1028Not measuredOnly Gemini 3.7 Flash measured
LiveBench research76.5%Not measuredOnly Gemini 3.7 Flash measured
LiveBench browser56.0%Not measuredOnly Gemini 3.7 Flash measured
LiveBench long agentic28.3%Not measuredOnly Gemini 3.7 Flash measured
SREBench (Vals AI)4.6%Not measuredOnly Gemini 3.7 Flash measured
Finance Agent (Vals AI)59.0%45.4%Gemini 3.7 Flash
Tax Agent Bench (Vals AI)22.8%8.8%Gemini 3.7 Flash
Legal Research Bench (Vals AI)34.6%12.5%Gemini 3.7 Flash
Excel Modeling Benchmark (Vals AI)71.3%45.4%Gemini 3.7 Flash
Terminal-Bench-Science (Vals AI)7.1%Not measuredOnly Gemini 3.7 Flash measured
τ²-Bench TelecomNot measured83.3%Only GPT-5.4 Mini measured
APEX-Agents67.8%Not measuredOnly Gemini 3.7 Flash measured
Remote Labor Index5.0%Not measuredOnly Gemini 3.7 Flash measured
DeepResearch BenchNot measured36.3%Only GPT-5.4 Mini measured
Neither model has a result on the other 18 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index140
Reasoning benchmarks for Gemini 3.7 Flash and GPT-5.4 Mini
BenchmarkGemini 3.7 FlashGPT-5.4 MiniLeader
GPQA Diamond93.9%83.1%Gemini 3.7 Flash
LiveBench reasoning87.8%Not measuredOnly Gemini 3.7 Flash measured
MMMU Pro (Vals AI)89.0%79.3%Gemini 3.7 Flash
GPQA Diamond (Artificial Analysis run)94.5%87.5%Gemini 3.7 Flash
Humanity's Last Exam (Artificial Analysis run)47.9%28.1%Gemini 3.7 Flash
GPQA Diamond (Epoch AI run)94.8%86.9%Gemini 3.7 Flash
ARC-AGI95.5%63.7%Gemini 3.7 Flash
ARC-AGI-284.6%18.9%Gemini 3.7 Flash
Chess puzzles66.0%23.0%Gemini 3.7 Flash
Mystery game puzzles37.0%11.0%Gemini 3.7 Flash
LMArena Text: hard prompts14951424Gemini 3.7 Flash
LMArena Text: expert15121435Gemini 3.7 Flash
LMArena Text: hard prompts in English14871420Gemini 3.7 Flash
LMArena Vision: diagrams13291266Gemini 3.7 Flash
LMArena Vision: homework13201285Gemini 3.7 Flash
Neither model has a result on the other 6 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index60
Math benchmarks for Gemini 3.7 Flash and GPT-5.4 Mini
BenchmarkGemini 3.7 FlashGPT-5.4 MiniLeader
AIMENot measured95.6%Only GPT-5.4 Mini measured
OTIS Mock AIME97.2%88.9%Gemini 3.7 Flash
FrontierMath, tiers 1 to 371.6%51.2%Gemini 3.7 Flash
FrontierMath, tier 436.6%9.8%Gemini 3.7 Flash
ProofBench58.0%21.0%Gemini 3.7 Flash
LMArena Text: math15111418Gemini 3.7 Flash
LMArena Text: mathematical work15021429Gemini 3.7 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 3.7 Flash and GPT-5.4 Mini
BenchmarkGemini 3.7 FlashGPT-5.4 MiniLeader
MMLU Pro90.1%84.5%Gemini 3.7 Flash
LegalBench (Vals AI)87.3%Not measuredOnly Gemini 3.7 Flash measured
CaseLaw (Vals AI)Not measured51.7%Only GPT-5.4 Mini measured
CorpFin (Vals AI)Not measured60.9%Only GPT-5.4 Mini measured
TaxEval (Vals AI)74.7%71.2%Gemini 3.7 Flash
MortgageTax (Vals AI)66.7%63.5%Gemini 3.7 Flash
MedCode (Vals AI)53.4%Not measuredOnly Gemini 3.7 Flash measured
SimpleQA Verified69.2%29.4%Gemini 3.7 Flash
LMArena Text: science15111417Gemini 3.7 Flash
LMArena Text: medicine and healthcare14941395Gemini 3.7 Flash
LMArena Text: legal and government14961414Gemini 3.7 Flash
LMArena Text: business and finance14791418Gemini 3.7 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 3.7 Flash and GPT-5.4 Mini
BenchmarkGemini 3.7 FlashGPT-5.4 MiniLeader
Design Arena: websites1304Not measuredOnly Gemini 3.7 Flash measured
Design Arena: UI components1299Not measuredOnly Gemini 3.7 Flash measured
Design Arena: game dev1318Not measuredOnly Gemini 3.7 Flash measured
Design Arena: data viz1315Not measuredOnly Gemini 3.7 Flash measured
Design Arena: 3D1308Not measuredOnly Gemini 3.7 Flash measured
Design Arena: all code categories1308Not measuredOnly Gemini 3.7 Flash measured
Design Arena: SVG1283Not measuredOnly Gemini 3.7 Flash measured
Design Arena: ASCII art1276Not measuredOnly Gemini 3.7 Flash measured
LiveBench design73.2%Not measuredOnly Gemini 3.7 Flash measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index261
General benchmarks for Gemini 3.7 Flash and GPT-5.4 Mini
BenchmarkGemini 3.7 FlashGPT-5.4 MiniLeader
LiveBench data analysis68.0%Not measuredOnly Gemini 3.7 Flash measured
SAGE (Vals AI)49.2%50.8%GPT-5.4 Mini
MedScribe (Vals AI)83.9%Not measuredOnly Gemini 3.7 Flash measured
Vals Multimodal IndexNot measured54.2%Only GPT-5.4 Mini measured
IFBenchNot measured73.3%Only GPT-5.4 Mini measured
Long context reasoning (AA-LCR)83.0%77.0%Gemini 3.7 Flash
DTBench96.8%80.0%Gemini 3.7 Flash
LMCA50.4%40.8%Gemini 3.7 Flash
Furniture assembly26.7%Not measuredOnly Gemini 3.7 Flash measured
LMArena Text14891412Gemini 3.7 Flash
LMArena Text: instruction following14841405Gemini 3.7 Flash
LMArena Text: creative writing14881370Gemini 3.7 Flash
LMArena Vision13141245Gemini 3.7 Flash
LMArena Text: English14831412Gemini 3.7 Flash
LMArena Text: non-English14871405Gemini 3.7 Flash
LMArena Text: Chinese15521446Gemini 3.7 Flash
LMArena Text: German15061408Gemini 3.7 Flash
LMArena Text: Japanese15111375Gemini 3.7 Flash
LMArena Text: Korean14811370Gemini 3.7 Flash
LMArena Text: French15001441Gemini 3.7 Flash
LMArena Text: Spanish14951405Gemini 3.7 Flash
LMArena Text: Russian15151417Gemini 3.7 Flash
LMArena Text: Polish15031415Gemini 3.7 Flash
LMArena Text: multi-turn14851429Gemini 3.7 Flash
LMArena Text: longer queries14921408Gemini 3.7 Flash
LMArena Text: writing and language14911393Gemini 3.7 Flash
LMArena Text: entertainment and media14771373Gemini 3.7 Flash
LMArena Vision: English13091244Gemini 3.7 Flash
LMArena Vision: Chinese13941286Gemini 3.7 Flash
LMArena Vision: reading text13221253Gemini 3.7 Flash
LMArena Vision: humor12991235Gemini 3.7 Flash
LMArena Vision: recognizing thingsNot measured1218Only GPT-5.4 Mini measured
LMArena Vision: creative writing13121222Gemini 3.7 Flash
Neither model has a result on the other 13 boards here
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
Image generation benchmarks for Gemini 3.7 Flash and GPT-5.4 Mini
BenchmarkGemini 3.7 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 3.7 Flash$0.0026Fits in one request
GPT-5.4 Mini$0.0030Fits in one request

Gemini 3.7 Flash costs less

Repository review

50K input + 3K output tokens

Gemini 3.7 Flash$0.049Fits in one request
GPT-5.4 Mini$0.051Fits in one request

Gemini 3.7 Flash costs less

Agent loop

200K input + 10K output tokens

Gemini 3.7 Flash$0.188Fits in one request
GPT-5.4 Mini$0.195Fits in one request

Gemini 3.7 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 3.7 Flash and GPT-5.4 Mini
SpecificationGoogle Gemini 3.7 FlashOpenAI GPT-5.4 Mini
MakerGoogleOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedAugust 13, 2026March 17, 2026
Context window1.05M400K
Input $/Mtok$0.75$0.75
Output $/Mtok$3.75$4.50
Coding index69.928.2
Independent measurements behind it21
Cost per solved task$1.78$0.70
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemini 3.7 Flash better than GPT-5.4 Mini for coding?

Pick Gemini 3.7 Flash for coding: it scores 69.9 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 $1.78, or when what matters is ALE-Bench or SAGE (Vals AI), where it leads.

Which is cheaper, Gemini 3.7 Flash or GPT-5.4 Mini?

Gemini 3.7 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 3.7 Flash costs $1.78 and GPT-5.4 Mini $0.70.

Which has the bigger context window, Gemini 3.7 Flash or GPT-5.4 Mini?

Gemini 3.7 Flash, with 1.05M tokens against 400K.

How many benchmarks is the Gemini 3.7 Flash vs GPT-5.4 Mini comparison based on?

77 benchmarks have a result for both models as of October 21, 2026. Gemini 3.7 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.

Compare next