LLMBenchmark.ai

Enter opens the highlighted result. Esc closes.

Gemini 3.5 Flash vs GPT-5 Mini

Updated October 21, 2026. 80 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.

Replace Gemini 3.5 Flash Replace GPT-5 Mini
Gemini 3.5 FlashGoogle
Coding
42.8
Overall
33.6
Output $/M
$9.00
78
GPT-5 MiniOpenAI
Coding
59.8
Overall
20.6
Output $/M
$2.00
2
vs boards won of 80 shared

Decision reading

Pick GPT-5 Mini for coding: it scores 59.8 on the Vibe Coding Index against 42.8 for Gemini 3.5 Flash.

Pick Gemini 3.5 Flash when the context window is larger, 1.05M against 400K tokens, or when what matters is LiveCodeBench (Vals AI) or SWE-bench Verified (Vals AI), where it leads.

Model AGemini 3.5 FlashGoogle42.8/1001 independent benchmark$1.21 per solved taskModel BGPT-5 MiniOpenAI59.8/1001 independent benchmark$0.08 per solved task
Shared results
80
Gemini 3.5 Flash only
30
GPT-5 Mini only
18
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 3.5 Flash 42.8 from 1 benchmark, GPT-5 Mini 59.8 from 1 benchmark.
Widest category
Agentic work, 29.1 points apart on average over 2 shared benchmarks.
Widest single gap
ARC-AGI-2: Gemini 3.5 Flash 72.1% against GPT-5 Mini 4.4%, 67.6 points apart on a 0 to 100 scale.
Output price
Gemini 3.5 Flash $9.00 against GPT-5 Mini $2.00 per million output tokens, 4.5x apart.
Context window
Gemini 3.5 Flash takes 1.05M tokens, GPT-5 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 MiniTies
Coding80
Intelligence20
Agentic work20
Reasoning140
Math60
Knowledge101
Web design80
General281
All shared boards782
CodingLike-for-likeFour of these boards feed the Vibe Coding Index80
Coding benchmarks for Gemini 3.5 Flash and GPT-5 Mini
BenchmarkGemini 3.5 FlashGPT-5 MiniLeader
SWE-bench VerifiedNot measured59.8%Only GPT-5 Mini measured
SWE-bench MultilingualNot measured39.7%Only GPT-5 Mini measured
LMArena WebDev1499Not measuredOnly Gemini 3.5 Flash measured
LiveCodeBench (Vals AI)87.6%86.6%Gemini 3.5 Flash
SWE-bench Verified (Vals AI)78.8%60.8%Gemini 3.5 Flash
Terminal-Bench 4 (Vals AI)6.1%Not measuredOnly Gemini 3.5 Flash measured
Vibe Code Bench (Vals AI)48.7%14.2%Gemini 3.5 Flash
Code migration (Vals AI)26.8%Not measuredOnly Gemini 3.5 Flash measured
ProgramBench (Vals AI)0.0%Not measuredOnly Gemini 3.5 Flash measured
Terminal-Bench 2.1 (Vals AI)74.2%Not measuredOnly Gemini 3.5 Flash measured
SkillsBench (Vals AI)52.7%Not measuredOnly Gemini 3.5 Flash measured
LiveCodeBench (Artificial Analysis run)Not measured83.8%Only GPT-5 Mini measured
SciCode53.9%39.0%Gemini 3.5 Flash
Terminal-Bench Hard (Artificial Analysis run)46.2%33.3%Gemini 3.5 Flash
Terminal-BenchNot measured34.8%Only GPT-5 Mini measured
WeirdML62.6%52.7%Gemini 3.5 Flash
ALE-Bench911.0Not measuredOnly Gemini 3.5 Flash measured
LMArena Text: coding14931406Gemini 3.5 Flash
LMArena Text: software and IT14941394Gemini 3.5 Flash
LMArena WebDev: React1495Not measuredOnly Gemini 3.5 Flash measured
LMArena WebDev: HTML1522Not measuredOnly Gemini 3.5 Flash measured
LMArena WebDev: from an image1504Not measuredOnly Gemini 3.5 Flash measured
Neither model has a result on the other 16 boards here
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
Intelligence benchmarks for Gemini 3.5 Flash and GPT-5 Mini
BenchmarkGemini 3.5 FlashGPT-5 MiniLeader
AA Intelligence Index33.620.6Gemini 3.5 Flash
Epoch Capabilities Index154.9145.3Gemini 3.5 Flash
Agentic workLike-for-likePublic boards, shown as published, kept out of the index20
Agentic work benchmarks for Gemini 3.5 Flash and GPT-5 Mini
BenchmarkGemini 3.5 FlashGPT-5 MiniLeader
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 apps1175Not measuredOnly Gemini 3.5 Flash measured
Design Arena: agents building Android apps1190Not 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 slides1142Not measuredOnly Gemini 3.5 Flash measured
Design Arena: PowerPoint slides1178Not measuredOnly Gemini 3.5 Flash measured
Finance Agent (Vals AI)57.9%Not measuredOnly Gemini 3.5 Flash measured
Tax Agent Bench (Vals AI)21.6%Not measuredOnly Gemini 3.5 Flash measured
Legal Research Bench (Vals AI)30.8%Not measuredOnly Gemini 3.5 Flash measured
Excel Modeling Benchmark (Vals AI)63.5%Not measuredOnly Gemini 3.5 Flash measured
Terminal-Bench-Science (Vals AI)5.7%Not measuredOnly Gemini 3.5 Flash measured
τ²-Bench Telecom95.6%71.1%Gemini 3.5 Flash
APEX-Agents27.5%Not measuredOnly Gemini 3.5 Flash measured
Vending-Bench 2$5,396-$31Gemini 3.5 Flash
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 Mini
BenchmarkGemini 3.5 FlashGPT-5 MiniLeader
GPQA Diamond92.7%80.3%Gemini 3.5 Flash
MMMU Pro (Vals AI)88.3%78.9%Gemini 3.5 Flash
GPQA Diamond (Artificial Analysis run)92.2%82.8%Gemini 3.5 Flash
Humanity's Last Exam (Artificial Analysis run)42.7%21.5%Gemini 3.5 Flash
GPQA Diamond (Epoch AI run)92.8%75.0%Gemini 3.5 Flash
ARC-AGI92.5%54.3%Gemini 3.5 Flash
ARC-AGI-272.1%4.4%Gemini 3.5 Flash
SimpleBench76.7%Not measuredOnly Gemini 3.5 Flash measured
Chess puzzles45.0%24.0%Gemini 3.5 Flash
Mystery game puzzles32.0%10.0%Gemini 3.5 Flash
EBR-bench4.8%Not measuredOnly Gemini 3.5 Flash measured
VPCTNot measured40.2%Only GPT-5 Mini measured
LMArena Text: hard prompts14881380Gemini 3.5 Flash
LMArena Text: expert14951379Gemini 3.5 Flash
LMArena Text: hard prompts in English14831383Gemini 3.5 Flash
LMArena Vision: diagrams13231202Gemini 3.5 Flash
LMArena Vision: homework13301210Gemini 3.5 Flash
Neither model has a result on the other 4 boards here
MathLike-for-likePublic boards, shown as published, kept out of the index60
Math benchmarks for Gemini 3.5 Flash and GPT-5 Mini
BenchmarkGemini 3.5 FlashGPT-5 MiniLeader
AIMENot measured91.5%Only GPT-5 Mini measured
MATH 500 (Vals AI)Not measured94.8%Only GPT-5 Mini measured
MGSM (Vals AI)Not measured92.6%Only GPT-5 Mini measured
AA Math IndexNot measured90.7Only GPT-5 Mini measured
AIME 2025 (Artificial Analysis run)Not measured90.7%Only GPT-5 Mini measured
OTIS Mock AIME95.6%86.7%Gemini 3.5 Flash
FrontierMath, tiers 1 to 362.8%46.7%Gemini 3.5 Flash
FrontierMath, tier 426.8%12.2%Gemini 3.5 Flash
ProofBench31.0%9.0%Gemini 3.5 Flash
MATH level 5Not measured97.8%Only GPT-5 Mini measured
LMArena Text: math15041378Gemini 3.5 Flash
LMArena Text: mathematical work14951380Gemini 3.5 Flash
Neither model has a result on the other 1 board here
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index101
Knowledge benchmarks for Gemini 3.5 Flash and GPT-5 Mini
BenchmarkGemini 3.5 FlashGPT-5 MiniLeader
MMLU Pro89.5%82.2%Gemini 3.5 Flash
LegalBench (Vals AI)83.6%81.8%Gemini 3.5 Flash
CaseLaw (Vals AI)Not measured68.5%Only GPT-5 Mini measured
CorpFin (Vals AI)64.7%60.2%Gemini 3.5 Flash
TaxEval (Vals AI)74.4%75.2%GPT-5 Mini
MortgageTax (Vals AI)68.1%66.9%Gemini 3.5 Flash
MedQA (Vals AI)Not measured96.1%Only GPT-5 Mini measured
MedCode (Vals AI)55.8%43.0%Gemini 3.5 Flash
MMLU Pro (Artificial Analysis run)Not measured83.7%Only GPT-5 Mini measured
SimpleQA Verified66.2%21.6%Gemini 3.5 Flash
LMArena Text: science14951371Gemini 3.5 Flash
LMArena Text: medicine and healthcare14831380Gemini 3.5 Flash
LMArena Text: legal and government14881375Gemini 3.5 Flash
LMArena Text: business and finance14671358Gemini 3.5 Flash
Neither model has a result on the other 3 boards here
Web designLike-for-likePublic boards, shown as published, kept out of the index80
Web design benchmarks for Gemini 3.5 Flash and GPT-5 Mini
BenchmarkGemini 3.5 FlashGPT-5 MiniLeader
Design Arena: websites12681125Gemini 3.5 Flash
Design Arena: UI components12721106Gemini 3.5 Flash
Design Arena: game dev12631130Gemini 3.5 Flash
Design Arena: data viz12361131Gemini 3.5 Flash
Design Arena: 3D12441037Gemini 3.5 Flash
Design Arena: all code categories12661115Gemini 3.5 Flash
Design Arena: SVG12541091Gemini 3.5 Flash
Design Arena: ASCII art12531124Gemini 3.5 Flash
Neither model has a result on the other 1 board here
GeneralLike-for-likePublic boards, shown as published, kept out of the index281
General benchmarks for Gemini 3.5 Flash and GPT-5 Mini
BenchmarkGemini 3.5 FlashGPT-5 MiniLeader
Public Benefits Bench (Vals AI)59.5%Not measuredOnly Gemini 3.5 Flash measured
SAGE (Vals AI)49.9%43.0%Gemini 3.5 Flash
MedScribe (Vals AI)76.6%80.6%GPT-5 Mini
Vals Multimodal Index62.9%Not measuredOnly Gemini 3.5 Flash measured
IFBench76.3%75.4%Gemini 3.5 Flash
Long context reasoning (AA-LCR)74.3%72.3%Gemini 3.5 Flash
DTBench94.7%80.5%Gemini 3.5 Flash
LMCA47.1%34.2%Gemini 3.5 Flash
Fiction.LiveBenchNot measured69.4%Only GPT-5 Mini measured
Creative writing (Lech Mazur)Not measured83.1%Only GPT-5 Mini measured
Surface Evolver Bench58.1%Not measuredOnly Gemini 3.5 Flash measured
LMArena Text14821373Gemini 3.5 Flash
LMArena Text: instruction following14671357Gemini 3.5 Flash
LMArena Text: creative writing14701325Gemini 3.5 Flash
LMArena Vision13081202Gemini 3.5 Flash
LMArena Text: English14811379Gemini 3.5 Flash
LMArena Text: non-English14751363Gemini 3.5 Flash
LMArena Text: Chinese15271386Gemini 3.5 Flash
LMArena Text: German14941366Gemini 3.5 Flash
LMArena Text: Japanese14861341Gemini 3.5 Flash
LMArena Text: Korean14481308Gemini 3.5 Flash
LMArena Text: French14901386Gemini 3.5 Flash
LMArena Text: Spanish14801354Gemini 3.5 Flash
LMArena Text: Russian14931362Gemini 3.5 Flash
LMArena Text: Polish15161378Gemini 3.5 Flash
LMArena Text: multi-turn14811363Gemini 3.5 Flash
LMArena Text: longer queries14831355Gemini 3.5 Flash
LMArena Text: writing and language14781344Gemini 3.5 Flash
LMArena Text: entertainment and media14591340Gemini 3.5 Flash
LMArena Vision: English13051216Gemini 3.5 Flash
LMArena Vision: Chinese13771214Gemini 3.5 Flash
LMArena Vision: reading text13171199Gemini 3.5 Flash
LMArena Vision: humor13211205Gemini 3.5 Flash
LMArena Vision: captioningNot measured1217Only GPT-5 Mini measured
LMArena Vision: recognizing thingsNot measured1226Only GPT-5 Mini measured
LMArena Vision: creative writing13011181Gemini 3.5 Flash
LMArena Document1463Not measuredOnly Gemini 3.5 Flash measured
Neither model has a result on the other 9 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 Mini
BenchmarkGemini 3.5 FlashGPT-5 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 Mini$0.0013Fits in one request

GPT-5 Mini costs less

Repository review

50K input + 3K output tokens

Gemini 3.5 Flash$0.102Fits in one request
GPT-5 Mini$0.018Fits in one request

GPT-5 Mini costs less

Agent loop

200K input + 10K output tokens

Gemini 3.5 Flash$0.390Fits in one request
GPT-5 Mini$0.070Fits in one request

GPT-5 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 Mini
SpecificationGoogle Gemini 3.5 FlashOpenAI GPT-5 Mini
MakerGoogleOpenAI
WeightsNo public weights listedNo public weights listed
ReleasedMay 19, 2026August 7, 2025
Context window1.05M400K
Input $/Mtok$1.50$0.25
Output $/Mtok$9.00$2.00
Coding index42.859.8
Independent measurements behind it11
Cost per solved task$1.21$0.08
SourceOpenRouter listingOpenRouter listing

Questions

Is Gemini 3.5 Flash better than GPT-5 Mini for coding?

Pick GPT-5 Mini for coding: it scores 59.8 on the Vibe Coding Index against 42.8 for Gemini 3.5 Flash. Pick Gemini 3.5 Flash when the context window is larger, 1.05M against 400K tokens, or when what matters is LiveCodeBench (Vals AI) or SWE-bench Verified (Vals AI), where it leads.

Which is cheaper, Gemini 3.5 Flash or GPT-5 Mini?

Gemini 3.5 Flash costs $1.50 per million input tokens and $9.00 per million output tokens; GPT-5 Mini costs $0.25 and $2.00. Per solved SWE-bench Verified task, Gemini 3.5 Flash costs $1.21 and GPT-5 Mini $0.08.

Which has the bigger context window, Gemini 3.5 Flash or GPT-5 Mini?

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

How many benchmarks is the Gemini 3.5 Flash vs GPT-5 Mini comparison based on?

80 benchmarks have a result for both models as of October 21, 2026. Gemini 3.5 Flash's coding index rests on 1 independent benchmark and GPT-5 Mini's on 1. Where only one model has a result, the page says so instead of naming a winner.

Compare next