LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Gemini 3.7 Flash vs GPT-5.4

Updated October 21, 2026. 89 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
Gemini 3.7 FlashGoogle
Coding
69.9
Overall
39.6
Output $/M
$3.75
78
GPT-5.4OpenAI
Coding
37.7
Overall
39.0
Output $/M
$15.00
10
vs boards won of 89 shared, 1 tied

Decision reading

Pick Gemini 3.7 Flash for coding: it scores 69.9 on the Vibe Coding Index against 37.7 for GPT-5.4.

Pick GPT-5.4 when a solved task costs $1.02 against $1.78, or when the context window is larger, 1.05M against 1.05M tokens.

Model AGemini 3.7 FlashGoogle69.9/1002 independent benchmarks$1.78 per solved taskModel BGPT-5.4OpenAI37.7/1001 independent benchmark$1.02 per solved task
Shared results
89
Gemini 3.7 Flash only
23
GPT-5.4 only
20
Like-for-like categories
8 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 37.7 from 1 benchmark.
Widest category
Agentic work, 20.0 points apart on average over 6 shared benchmarks.
Widest single gap
Design Arena: 3D: Gemini 3.7 Flash 1308 against GPT-5.4 1065, 30.4 points apart on a 0 to 100 scale.
Output price
Gemini 3.7 Flash $3.75 against GPT-5.4 $15.00 per million output tokens, 4.0x apart.
Context window
Gemini 3.7 Flash takes 1.05M tokens, GPT-5.4 1.05M.

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-5.4Ties
Coding113
Intelligence20
Agentic work60
Reasoning1211 tie
Math33
Knowledge91
Web design80
General272
All shared boards78101 tie
CodingLike-for-likeFour of these boards feed the Vibe Coding Index113
Coding benchmarks for Gemini 3.7 Flash and GPT-5.4
BenchmarkGemini 3.7 FlashGPT-5.4Leader
LiveBench coding80.5%Not measuredOnly Gemini 3.7 Flash measured
LMArena WebDev15911464Gemini 3.7 Flash
AA Coding Index71.571.1Gemini 3.7 Flash
LiveCodeBench (Vals AI)88.7%84.1%Gemini 3.7 Flash
SWE-bench Verified (Vals AI)80.8%78.2%Gemini 3.7 Flash
Terminal-Bench 4 (Vals AI)12.1%Not measuredOnly Gemini 3.7 Flash measured
Vibe Code Bench (Vals AI)70.4%67.4%Gemini 3.7 Flash
Code migration (Vals AI)34.8%35.0%GPT-5.4
ProgramBench (Vals AI)0.0%0.5%GPT-5.4
IOI (Vals AI)67.8%Not measuredOnly Gemini 3.7 Flash measured
Terminal-Bench 2.1 (Vals AI)77.5%Not measuredOnly Gemini 3.7 Flash measured
SkillsBench (Vals AI)65.9%51.7%Gemini 3.7 Flash
CyberBench (Vals AI)43.8%Not measuredOnly Gemini 3.7 Flash measured
SciCode59.8%Not measuredOnly Gemini 3.7 Flash measured
Terminal-Bench Hard (Artificial Analysis run)Not measured57.6%Only GPT-5.4 measured
Terminal-BenchNot measured81.8%Only GPT-5.4 measured
FrontierCode43.6%Not measuredOnly Gemini 3.7 Flash measured
FrontierSWE20.3%Not measuredOnly Gemini 3.7 Flash measured
GSO-BenchNot measured31.4%Only GPT-5.4 measured
WeirdMLNot measured77.7%Only GPT-5.4 measured
MirrorCodeNot measured15.6%Only GPT-5.4 measured
ALE-Bench904.31607.0GPT-5.4
LMArena Text: coding14991496Gemini 3.7 Flash
LMArena Text: software and IT14981491Gemini 3.7 Flash
LMArena WebDev: React15871454Gemini 3.7 Flash
LMArena WebDev: HTML15931478Gemini 3.7 Flash
LMArena WebDev: from an image15991436Gemini 3.7 Flash
Neither model has a result on the other 11 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
BenchmarkGemini 3.7 FlashGPT-5.4Leader
AA Intelligence Index39.639.0Gemini 3.7 Flash
Epoch Capabilities Index158.0157.3Gemini 3.7 Flash
Agentic workLike-for-likePublic boards, shown as published, kept out of the index60
Agentic work benchmarks for Gemini 3.7 Flash and GPT-5.4
BenchmarkGemini 3.7 FlashGPT-5.4Leader
Design Arena: agents building web apps12241059Gemini 3.7 Flash
Design Arena: agents building full-stack apps12081017Gemini 3.7 Flash
Design Arena: agents building mobile apps12301087Gemini 3.7 Flash
Design Arena: agents building Android apps12471037Gemini 3.7 Flash
Design Arena: agents building Godot games12641135Gemini 3.7 Flash
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%Not measuredOnly Gemini 3.7 Flash measured
Tax Agent Bench (Vals AI)22.8%Not measuredOnly Gemini 3.7 Flash measured
Legal Research Bench (Vals AI)34.6%Not measuredOnly Gemini 3.7 Flash measured
Excel Modeling Benchmark (Vals AI)71.3%Not measuredOnly Gemini 3.7 Flash measured
Terminal-Bench-Science (Vals AI)7.1%Not measuredOnly Gemini 3.7 Flash measured
τ²-Bench TelecomNot measured87.1%Only GPT-5.4 measured
APEX-Agents67.8%52.4%Gemini 3.7 Flash
METR time horizonsNot measured74.3%Only GPT-5.4 measured
Remote Labor Index5.0%Not measuredOnly Gemini 3.7 Flash measured
DeepResearch BenchNot measured35.1%Only GPT-5.4 measured
PostTrainBenchNot measured19.0%Only GPT-5.4 measured
Vending-Bench 2Not measured$6,144Only GPT-5.4 measured
Neither model has a result on the other 16 boards here
ReasoningLike-for-likePublic boards, shown as published, kept out of the index121
Reasoning benchmarks for Gemini 3.7 Flash and GPT-5.4
BenchmarkGemini 3.7 FlashGPT-5.4Leader
GPQA Diamond93.9%91.7%Gemini 3.7 Flash
LiveBench reasoning87.8%Not measuredOnly Gemini 3.7 Flash measured
MMMU Pro (Vals AI)89.0%87.5%Gemini 3.7 Flash
GPQA Diamond (Artificial Analysis run)94.5%92.0%Gemini 3.7 Flash
Humanity's Last Exam (Artificial Analysis run)47.9%43.7%Gemini 3.7 Flash
GPQA Diamond (Epoch AI run)94.8%93.3%Gemini 3.7 Flash
ARC-AGI95.5%93.7%Gemini 3.7 Flash
ARC-AGI-284.6%74.0%Gemini 3.7 Flash
Chess puzzles66.0%48.0%Gemini 3.7 Flash
Mystery game puzzles37.0%37.0%Tie
EBR-benchNot measured25.4%Only GPT-5.4 measured
LMArena Text: hard prompts14951485Gemini 3.7 Flash
LMArena Text: expert15121507Gemini 3.7 Flash
LMArena Text: hard prompts in English14871479Gemini 3.7 Flash
LMArena Vision: diagrams13291327Gemini 3.7 Flash
LMArena Vision: homework13201336GPT-5.4
Neither model has a result on the other 5 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index33
Math benchmarks for Gemini 3.7 Flash and GPT-5.4
BenchmarkGemini 3.7 FlashGPT-5.4Leader
AIMENot measured96.7%Only GPT-5.4 measured
OTIS Mock AIME97.2%97.8%GPT-5.4
FrontierMath, tiers 1 to 371.6%78.6%GPT-5.4
FrontierMath, tier 436.6%49.0%GPT-5.4
ProofBench58.0%56.0%Gemini 3.7 Flash
LMArena Text: math15111488Gemini 3.7 Flash
LMArena Text: mathematical work15021497Gemini 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 index91
Knowledge benchmarks for Gemini 3.7 Flash and GPT-5.4
BenchmarkGemini 3.7 FlashGPT-5.4Leader
MMLU Pro90.1%87.5%Gemini 3.7 Flash
LegalBench (Vals AI)87.3%86.0%Gemini 3.7 Flash
CaseLaw (Vals AI)Not measured63.8%Only GPT-5.4 measured
CorpFin (Vals AI)Not measured65.3%Only GPT-5.4 measured
TaxEval (Vals AI)74.7%74.0%Gemini 3.7 Flash
MortgageTax (Vals AI)66.7%68.3%GPT-5.4
MedQA (Vals AI)Not measured96.1%Only GPT-5.4 measured
MedCode (Vals AI)53.4%41.3%Gemini 3.7 Flash
SimpleQA Verified69.2%45.1%Gemini 3.7 Flash
LMArena Text: science15111479Gemini 3.7 Flash
LMArena Text: medicine and healthcare14941458Gemini 3.7 Flash
LMArena Text: legal and government14961486Gemini 3.7 Flash
LMArena Text: business and finance14791474Gemini 3.7 Flash
Neither model has a result on the other 4 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index80
Web design benchmarks for Gemini 3.7 Flash and GPT-5.4
BenchmarkGemini 3.7 FlashGPT-5.4Leader
Design Arena: websites13041199Gemini 3.7 Flash
Design Arena: UI components12991215Gemini 3.7 Flash
Design Arena: game dev13181195Gemini 3.7 Flash
Design Arena: data viz13151196Gemini 3.7 Flash
Design Arena: 3D13081065Gemini 3.7 Flash
Design Arena: all code categories13081180Gemini 3.7 Flash
Design Arena: SVG12831141Gemini 3.7 Flash
Design Arena: ASCII art12761188Gemini 3.7 Flash
LiveBench design73.2%Not measuredOnly Gemini 3.7 Flash measured
GeneralLike-for-likePublic boards, shown as published, kept out of the index272
General benchmarks for Gemini 3.7 Flash and GPT-5.4
BenchmarkGemini 3.7 FlashGPT-5.4Leader
LiveBench data analysis68.0%Not measuredOnly Gemini 3.7 Flash measured
SAGE (Vals AI)49.2%43.3%Gemini 3.7 Flash
MedScribe (Vals AI)83.9%77.5%Gemini 3.7 Flash
IFBenchNot measured73.9%Only GPT-5.4 measured
Long context reasoning (AA-LCR)83.0%82.0%Gemini 3.7 Flash
DTBench96.8%94.4%Gemini 3.7 Flash
LMCA50.4%52.0%GPT-5.4
CL-benchNot measured27.9%Only GPT-5.4 measured
Furniture assembly26.7%37.5%GPT-5.4
CL-bench LifeNot measured21.7%Only GPT-5.4 measured
LMArena Text14891469Gemini 3.7 Flash
LMArena Text: instruction following14841469Gemini 3.7 Flash
LMArena Text: creative writing14881439Gemini 3.7 Flash
LMArena Vision13141303Gemini 3.7 Flash
LMArena Text: English14831467Gemini 3.7 Flash
LMArena Text: non-English14871465Gemini 3.7 Flash
LMArena Text: Chinese15521520Gemini 3.7 Flash
LMArena Text: German15061472Gemini 3.7 Flash
LMArena Text: Japanese15111485Gemini 3.7 Flash
LMArena Text: Korean14811449Gemini 3.7 Flash
LMArena Text: French15001493Gemini 3.7 Flash
LMArena Text: Spanish14951452Gemini 3.7 Flash
LMArena Text: Russian15151480Gemini 3.7 Flash
LMArena Text: Polish15031472Gemini 3.7 Flash
LMArena Text: multi-turn14851482Gemini 3.7 Flash
LMArena Text: longer queries14921473Gemini 3.7 Flash
LMArena Text: writing and language14911458Gemini 3.7 Flash
LMArena Text: entertainment and media14771438Gemini 3.7 Flash
LMArena Vision: English13091301Gemini 3.7 Flash
LMArena Vision: Chinese13941354Gemini 3.7 Flash
LMArena Vision: reading text13221312Gemini 3.7 Flash
LMArena Vision: humor12991284Gemini 3.7 Flash
LMArena Vision: recognizing thingsNot measured1251Only GPT-5.4 measured
LMArena Vision: creative writing13121283Gemini 3.7 Flash
LMArena DocumentNot measured1471Only GPT-5.4 measured
Neither model has a result on the other 11 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
BenchmarkGemini 3.7 FlashGPT-5.4Leader
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$0.010Fits 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$0.170Fits 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$0.650Fits 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
SpecificationGoogle Gemini 3.7 FlashOpenAI GPT-5.4
MakerGoogleOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedAugust 13, 2026March 5, 2026
Context window1.05M1.05M
Input $/Mtok$0.75$2.50
Output $/Mtok$3.75$15.00
Coding index69.937.7
Independent measurements behind it21
Cost per solved task$1.78$1.02
SourceOpenRouter listingOpenRouter listing

Questions

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

Pick Gemini 3.7 Flash for coding: it scores 69.9 on the Vibe Coding Index against 37.7 for GPT-5.4. Pick GPT-5.4 when a solved task costs $1.02 against $1.78, or when the context window is larger, 1.05M against 1.05M tokens.

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

Gemini 3.7 Flash costs $0.75 per million input tokens and $3.75 per million output tokens; GPT-5.4 costs $2.50 and $15.00. Per solved SWE-bench Verified task, Gemini 3.7 Flash costs $1.78 and GPT-5.4 $1.02.

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

GPT-5.4, with 1.05M tokens against 1.05M.

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

89 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's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next